Hands-on AI security engineer role focusing on discovering, understanding, and mitigating risks across enterprise AI and agentic platforms. Responsibilities include researching emerging AI threats, developing threat models and data models for AI assets and attack paths, building backend services and APIs for AI asset discovery and risk assessment, creating detection rules for suspicious AI activity, developing scalable security telemetry pipelines, and collaborating with security research and detection engineering teams to validate threats and improve coverage.
Design, build, and deploy machine learning systems for threat detection and response. Build and fine-tune models for threat detection, anomaly detection, and behavioral modeling. Implement LLM-powered agents for reasoning over security data and develop RAG pipelines. Work with streaming security data (logs, events, alerts) to train and evaluate models. Collaborate across research, backend, and security teams to deploy models in scalable, low-latency environments.
Lead hands-on research designing and building AI agents that secure the software development lifecycle. Research and prototype solutions using AI agents for secure design, code review, vulnerability discovery, and automated remediation. Design novel agent-based security capabilities end-to-end from proof of concept to production. Build benchmarks and evaluation methods measuring AI agent performance on real-world security tasks. Requires 5+ years security research/engineering experience, extensive hands-on AI/agent engineering with frontier models, and deep SDLC security foundations including threat modeling and vulnerability research.
ML or research engineer role focused on detecting and mitigating AI system misuse. Responsibilities include building classifiers for misuse detection, developing synthetic data pipelines, creating systems to monitor coordinated attacks and influence operations, evaluating agentic product safety with threat modeling and prompt injection mitigations, and conducting automated red-teaming research. Requires 4+ years ML/research engineering experience, Python proficiency, and comfort across research-to-deployment pipelines. Strong candidates have language modeling, anomaly detection, adversarial ML, or red-teaming experience.
Design and build AI/ML-driven security platforms at Cisco, integrating LLMs for threat detection, anomaly analysis, and intelligent policy enforcement. Architect security-first, cloud-native systems with Zero Trust and runtime security capabilities. Develop large-scale telemetry and real-time inference systems. Lead hands-on design and development across the AI security lifecycle, including model protection, access control, and runtime enforcement. Requires 12+ years in platform/security engineering with expertise in cloud-native security, LLM applications, and large-scale distributed systems.
Build next-generation Agentic SOC platforms and orchestration systems that enable trusted AI agents across Cisco and Splunk security products. Design shared capabilities spanning agent runtime, orchestration, governed tool use, evaluation systems, and quality gates. Translate SOC, SIEM, detection, and incident response needs into AI mechanisms. Define measurable success criteria for AI in security (task completion, groundedness, tool-use correctness, safety, latency). Establish metrics-driven development using golden datasets, offline/online evaluations, and production traces. Architect for multiple deployment environments with data residency, auditability, and permission-aware actions. Mentor senior engineers and raise engineering standards across teams.
AI Information Security Engineer at Tenable responsible for designing and implementing end-to-end security controls across the AI/ML lifecycle. Responsibilities include securing LLMs and agentic AI workflows, conducting AI safety assessments and threat modeling, identifying risks such as data poisoning and model evasion, developing security reference architectures, and building AI-driven security tooling. Requires hands-on AI engineering experience combined with application security expertise and knowledge of adversarial ML techniques.
AI Security Engineer responsible for securing Amazon's AI applications through threat modeling, code review, and security automation. Develops frameworks and tools to help development teams build secure AI software, performs security research and risk assessments, and provides AI security architecture guidance. Works across Java, Python, and JavaScript codebases to identify and mitigate AI security risks affecting millions of customers.
NVIDIA is seeking a Distinguished Engineer to lead the founding of an AI Safety & Security Engineering team. The role involves architecting core harness systems for AI-powered vulnerability discovery, validation, and patching. Key responsibilities include defining canonical harness architecture, establishing engineering standards, guiding the find-validate-patch technical roadmap, and mentoring founding engineers. The position bridges exploratory AI security research with production-grade engineering, requiring 18+ years of complex systems design experience, architecture depth in distributed systems or ML pipelines, proven ability to translate research into production, and collaboration across engineering and research teams. Security and vulnerability research experience is valued, as is familiarity with agent frameworks and LLM-based tooling.
Set security design standards and architecture for NVIDIA DGX Cloud, an AI factory securing hundreds of thousands of GPUs. Responsibilities include defining tenancy and GPU workload isolation, architecting security platforms with hardened baselines and detection systems, threat modeling distributed AI systems, embedding with teams on implementation, and leading a team of Principal Engineers. Scope spans hardware root of trust through services and APIs, with focus on emerging AI threats including AI-generated code, AI-assisted attacks, and autonomous agents.
Security engineer at NVIDIA focusing on automating security enforcement across GPU software releases using AI agents and traditional tooling. Responsibilities include leading adoption of AI agents in security workflows, translating security requirements into automated per-release checks, owning the release security scanning pipeline, and collaborating on threat modeling and vulnerability mitigation. Requires 5+ years of security engineering experience with drivers/kernel/firmware, strong Python and C skills, hands-on experience building LLM agents, and CI/CD integration expertise.
Lead Alice Labs' research agenda in AI safety, security, and model evaluation. Design benchmarks and evaluation frameworks to surface vulnerabilities in frontier AI models. Conduct red teaming and adversarial robustness research on LLMs, agents, and multimodal systems. Ship three new benchmarks monthly, one breakthrough quarterly, and publish papers at top-tier conferences (NeurIPS, ICML, ICLR, ACL, IEEE S&P). Build research relationships with frontier labs and academic institutions. Translate research findings into products at scale through collaboration with engineering and product teams.
Lead researcher conducting embedded evaluations at frontier AI labs to detect deceptive alignment, scheming, and loss-of-control risks. Responsibilities include designing and executing evaluation methodologies, developing tooling for evidence gathering, analyzing model behaviors and training processes, identifying safety gaps, and producing high-stakes technical reports for lab leadership and governance teams. Requires expertise in alignment research, model evaluation, adversarial techniques, and ability to lead ambitious technical projects under deadline pressure.
Principal engineer designing and building agentic identity and security infrastructure for AI agent workflows at NVIDIA. Responsibilities include architecting agent identity capabilities, credential brokering, token delegation, and lifecycle management; prototyping solutions for agent-specific security risks including prompt injection and unauthorized access expansion; building reusable APIs and integration patterns; and collaborating across security, product, and platform teams. Requires 15+ years in security engineering, hands-on technical leadership, offensive security/red teaming experience, and expertise in identity standards and cloud infrastructure.
Principal-level security architect for NVIDIA DGX Cloud AI platform. Owns core security domains including tenant/GPU isolation, workload identity, infrastructure security, and policy enforcement. Responsibilities include end-to-end architectural ownership, threat modeling complex distributed AI systems, embedding security into platform design, writing production code, and engineering systematic security solutions. Collaborates across platform teams to build secure-by-default paths and eliminate classes of risk. Requires 15+ years experience in software engineering, SRE, infrastructure, and security engineering with proven track record securing production systems.
Own design and implementation of runtime policy verification, signed policy management, and governance infrastructure for agentic systems. Build conformance testing, fuzz testing, and security verification suites. Lead cross-team collaboration on runtime context attestation, adapter approval, and agent action enforcement. Define versioning, schema compatibility, and fail-closed security defaults. Requires 15+ years in systems software or security engineering with expertise in authorization systems, cryptographic signatures, trust roots, revocation, and zero-trust architecture.
Architect and build enterprise AI defense platforms at Cisco, securing foundation models, autonomous agents, and Model Context Protocol (MCP) tool execution. Design control planes, data planes, and policy engines that defend against prompt injection, model jailbreaks, and agent misuse. Develop high-throughput microservices in Go/Python to process security telemetry streams under strict SLAs. Implement zero-trust security boundaries, runtime guardrails, and automated remediation engines for enterprise AI workflows. Lead cross-functional strategy with Security Research and platform teams to establish industry standards for AI defense at global enterprise scale.
US (multiple: Mountain View CA, Boston MA, Arlington VA, New York NY, Dallas TX, Seattle WA)
Security Engineer embedded with AWS Forward Deployed Engineering teams to secure production AI systems deployed in customer environments. Responsibilities include conducting security design and code reviews for agentic workflows and RAG pipelines, performing threat modeling and penetration testing, building security automation and CI/CD gates, implementing AI-specific threat controls (prompt injection prevention, output filtering, guardrail configuration), supporting incident response for production AI systems, and developing reusable security playbooks and reference configurations.
Security research engineer advancing AI-powered tooling for vulnerability validation and patching. Develops techniques to confirm vulnerabilities are real and reachable, advances approaches for generating and verifying safe fixes, and defines correctness and regression standards. Works with AI-assisted workflows for analysis and development while maintaining critical evaluation of AI outputs. Requires 12+ years in security research or software engineering with hands-on vulnerability research, fuzzing, program analysis, or secure development experience in C, C++, or Python.
Senior engineer building secure agentic AI systems and cybersecurity tooling. Responsible for transforming research prototypes into production-ready services that enable secure agent deployment across enterprise platforms. Develops APIs, backend services, and reusable frameworks addressing AI-specific security risks including prompt injection, tool misuse, unauthorized access expansion, and unsafe delegation patterns. Collaborates with research, product, and security teams to align architecture with enterprise workflow needs while applying offensive security and red-teaming perspectives to security decisions.
AI security researcher focused on advancing protection of AI models, systems, and infrastructure through novel research and tool development. Responsibilities include researching cybersecurity and AI safety, developing techniques to expose and remediate weaknesses in AI and conventional systems, and publishing findings in peer-reviewed venues. Requires 5+ years in ML/cybersecurity with expertise in generative AI workflows, adversarial machine learning, and secure software development.
Lead research on AI models and agents for cybersecurity. Advance capabilities in security reasoning, code understanding, planning, tool use, and human-defender collaboration. Apply these to vulnerability discovery, threat detection, malware analysis, incident investigation, security validation, and automated defense. Develop robust, explainable AI-powered security capabilities for real operational environments. Build prototypes in realistic settings and collaborate across AI, security, and engineering teams to translate research into deployed systems.
Lead research on AI-enabled secure system design, analysis, implementation, and verification. Develop AI models, agents, and tools for security requirements, threat modeling, architecture exploration, secure code/hardware generation, program analysis, synthesis, and proof construction. Build end-to-end prototypes combining AI techniques with formal verification, static/dynamic analysis, and testing on realistic hardware and software systems. Collaborate across hardware, software, and AI teams to translate foundational advances into practical security capabilities.
Design and implement security guardrails for AI code-generation systems. Build shift-left solutions embedding security standards into AI agent output through constraint injection, rules, and scaffolds. Engineer verification workflows and evaluation harnesses to ensure generated code meets security compliance. Convert security architecture patterns into enterprise-grade reference implementations. Collaborate with teams adopting AI tooling to review builds, validate conformance, and establish technical standards for secure AI systems at scale.
Build and deliver production-ready governance infrastructure for AI agents. Implement policy verification engines, runtime integrations, and conformance testing for Agent Policy Fabric. Design and validate authorization systems, signed policy validation, and audit mechanisms to govern agent actions safely. Work on security controls including signature verification, credential mediation, and runtime policy enforcement across enterprise systems.
Lead technical authority for AI Defense at Cisco, owning systems that detect, validate, and stop threats to enterprise AI platforms and agents. Architect scalable, high-performance platform services protecting AI applications in real time. Drive LLM inference security strategy, design low-latency secure deployments, and partner with threat research and operations to deliver production-grade AI security capabilities. Hands-on technical leadership mentoring engineers across complex distributed systems and AI security challenges.
Support technical research and AI safety evaluations by assessing AI-generated chemistry content for scientific accuracy and safety risks. Evaluate organic synthesis approaches and AI-enabled chemistry tools through a dual-use security lens. Identify failure modes, technical inaccuracies, and security concerns in AI-generated chemical information. Collaborate with cross-functional teams to develop evaluation criteria and research methodologies for assessing chemical threats and AI capabilities. Requires advanced degree in chemistry and expertise in dual-use chemical research, with preferred experience in AI safety evaluations and adversarial testing.
Research engineer at Google DeepMind focused on responsible frontier AI. Responsibilities include prototyping scalable engineering solutions for safety research, architecting training and inference pipelines to detect and evaluate harmful manipulation behaviors in frontier language models, developing post-training strategies to mitigate manipulation risks including deceptive persuasion and sycophancy, collaborating with research scientists to translate safety research into implementations, and building evaluation infrastructure to track model safety performance across releases.
Research scientist focused on proactive threat mitigation, adversarial machine learning, and agentic security. Develops foundational ML research in model robustness, continual learning, and interpretability. Designs evaluation protocols and stress-testing methodologies for frontier AI capabilities. Curates datasets and conducts optimization experiments to enhance model resilience against emerging threats. Collaborates with engineering teams and academic partners on trustworthy AI solutions.
Security researcher at Alice focused on emerging agent risks and vulnerabilities in enterprise AI deployments. Responsibilities include studying how agents fail across tool calling, retrieval, memory, and multi-agent scenarios; building reproducible test environments and detectors for agent misbehavior; and translating research findings into platform guardrails and red-team tests. Publish technical research on agent security risks with responsible disclosure and CVE coordination. Collaborate with product, engineering, and foundation model labs to identify and validate threats.
Senior research scientist role focused on proactive threat mitigation, adversarial machine learning, and agentic security. Responsibilities include driving ML research in model robustness, interpretability, and multiobjective optimization; designing rigorous evaluation protocols and stress-testing methodologies for frontier AI capabilities; curating datasets and conducting fine-tuning experiments to enhance model resilience against emerging threats; and collaborating with engineering teams and academic partners. Requires PhD in CS or related field, 2+ years leading research agenda, and expertise in adversarial ML, AI safety, generative models, and agentic AI.
Junior Offensive Security Researcher at Zenity focused on discovering new attack vectors and exploits in agentic AI, LLMs, and their ecosystem. Responsibilities include researching emerging agentic technologies, building attack discovery tooling and test frameworks, investigating surrounding components (plugins, connectors, MCP servers, orchestration frameworks), and collaborating with product teams to translate offensive findings into defense capabilities. Requires red team/vulnerability research background, Python/JavaScript/bash coding skills, cloud and appsec experience, and AI vulnerability knowledge.
Designs, architects, and secures AI solutions across multi-cloud environments (GCP, Azure, AWS). Establishes security guardrails for AI agents, manages governance of AI vendor subscriptions (Anthropic, OpenAI, Gemini), and conducts security reviews of AI-enabled applications. Implements security controls for LLM integrations, designs data protection and compliance mechanisms, and maintains AI security policies and standards. Requires hands-on cloud security expertise, ML pipeline knowledge, and deep understanding of AI-specific threats including prompt injection, adversarial attacks, model extraction, and data poisoning.
Develops and maintains agentic AI toolchains for automated vulnerability identification and assessment in automotive software and vehicle systems. Designs AI-powered methods for detecting vulnerabilities in source code and binary code using commercial and open-source models. Implements fuzzing, penetration testing, and security analysis workflows. Integrates new AI models and agents into security assessment pipelines. Requires several years of automotive cybersecurity experience, expertise in building agentic AI systems, and complex security toolchain development.
Build AI agent workflows automating alert triage, threat modeling, and guided incident response. Design secure AWS cloud foundations with IAM, encryption, and network segmentation. Implement CI/CD automation with container security tooling (SAST/DAST/SCA). Conduct threat modeling for microservices, APIs, Kubernetes, and AI/LLM applications. Automate compliance and audit readiness for SOC 2, FedRAMP, ISO 27001 using Python, APIs, and Infrastructure-as-Code. Requires 7+ years hands-on cloud security, application security, or software engineering experience.
Paid research residency program at Anthropic lasting 6 weeks to 6 months. Residents work on empirical AI safety and security research including adversarial robustness, frontier red-teaming, safeguards development, model interpretability, and scalable oversight. Direct mentorship from AI safety researchers and access to Claude models and GPU compute. Open to experienced technical professionals transitioning to full-time AI safety work. Compensation $350K-$500K annually, pro-rated.
Design, build and ship safeguards for AI agents addressing prompt injection, jailbreaks, toxicity, and sensitive data exposure. Build evals measuring safeguard efficacy using adversarial testing and production data. Collaborate with security teams to integrate adversarial findings into mitigations. Select and fine-tune detection models for request-path controls. Balance quality, latency, and cost. Configure safeguard policies for customer control and monitor production behavior.
Senior Staff Security Engineer responsible for AI safeguard architecture and testing across ML-powered products. Leads security design of new ML features, conducts adversarial testing including jailbreak and prompt injection attacks, develops evaluation cases for safeguard validation, and designs mitigations in collaboration with ML engineers. Defines security metrics to assess safeguard effectiveness, reviews changes for weakness introduction, and translates emerging AI attack research into defensive tests and countermeasures.
Security-focused DevSecOps engineer joining Cisco's AI Software and Platform Group to improve security outcomes of core AI products. Responsibilities include driving shift-left security strategy, performing adversarial red teaming on internal AI products, leading security architecture reviews and threat modeling, operationalizing vulnerability management, and managing risk assessment. Requires 7+ years information security/DevOps experience, 2+ years with AI Agents for security testing, and expertise in CNAPP tools, cloud infrastructure security, and compliance assurance.
Security-focused DevSecOps leader within Cisco's AI Software and Platform Group responsible for securing AI-powered offerings including Cisco Cloud Control, AI Defense, and AI Canvas. Drives shift-left security strategies, performs security architecture reviews, leads threat modeling exercises, and conducts adversarial red teaming on internal AI products. Manages compliance efforts, operationalizes vulnerability management, secures runtime workloads and cloud infrastructure, and maintains risk registers to guide security decision-making across the organization.
Remote - International (Argentina, Poland, Italy, Romania, Netherlands, Spain, Portugal)
Lead AI-driven automation initiatives for client-facing cybersecurity services at VerSprite, a leading cybersecurity consulting firm. Identify opportunities to apply AI models and software engineering techniques to solve security challenges. Guide development and implementation of AI-powered security solutions. Mentor software engineers and technical cybersecurity professionals. Provide technical guidance on system architecture and automation. Work with senior client stakeholders and VerSprite leadership on technical priorities and service innovation.
Machine Learning Engineer at Carnegie Mellon University's Software Engineering Institute (SEI) Secure AI Lab, focused on research into vulnerabilities of AI/ML algorithms and securing against those vulnerabilities. Primary responsibilities include counter-AI research to study threat models and identify AI weaknesses, designing novel defenses against adversarial attacks, advanced adversarial machine learning, building ML models and systems using TensorFlow/PyTorch, technical experimentation, security testing and evaluation, and transitioning capabilities to government sponsors. Requires comprehensive ML knowledge with adversarial ML experience desirable, strong engineering practices, and ability to convert research into prototypes.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)AI lab
Experienced offensive security engineer at UK Government AI Security Institute building and breaking security controls for frontier AI model evaluations. Responsibilities include attacking evaluation sandboxes (container/VM escape, egress controls), finding vulnerabilities in the Inspect open-source evaluation framework, coordinating security fixes, and building agent-assisted red-teaming harnesses for continuous infrastructure testing. Works directly with engineering and research teams on cyber ranges and evaluation tasks with publication opportunities.
Technical lead role building agentic AI systems for security operations at Cisco. Responsibilities include designing and implementing AI agent runtime, orchestration, evaluation frameworks, and production trace analysis systems. Focus on creating trusted agentic capabilities for threat detection, investigation, and response across cloud, on-premises, and air-gapped environments. Requires expertise in LLM systems, agent behavior evaluation, tool governance, and SOC/SIEM domain knowledge. Involves implementing security controls for identity, authorization, tenancy, and auditability in production AI systems operating at scale for security teams.
Design and architect AI/ML-driven outbound security systems for enterprise SaaS platform. Responsibilities include building anomaly detection for egress traffic, ML-assisted destination risk scoring, and AI-assisted code review for SSRF prevention. Architect mission-critical egress services with AI/ML inference at scale on Kubernetes, handle incident response, threat modeling, and mentor teams on secure coding and outbound-request security patterns.
Develop and operate agentic AI workflows for vulnerability analysis and assessment. Build production LLM-powered systems to evaluate security vulnerability applicability to codebases, improve system output correctness through data sources and feedback loops, design scaling infrastructure, and validate outputs with vulnerability analysts. Requires 7+ years software development, Python proficiency, production LLM experience, and cloud platform expertise.
Hands-on AI Security Platform Engineer at Lenovo Digital Trust Lab responsible for designing and maintaining platform infrastructure for AI Controls Platform. Build data pipelines for collecting and analyzing AI security telemetry, implement automated analytics and continuous monitoring of AI security controls, and design agentic feedback loops using production data to identify and remediate AI security gaps. Establish infrastructure for model evaluation, experimentation, and deployment workflows. Work across AI security research, engineering, data science, and product teams to operationalize AI security capabilities across cloud, on-premises, and edge environments.
Senior researcher at CMU SEI applying AI/ML techniques to code analysis, reverse engineering, and malware detection/classification. Design and develop analysis methods and tools, identify emerging threats, and contribute to security community through research and presentations. Requires expertise in predictive modeling, modern ML frameworks (PyTorch, TensorFlow), LLMs/agentic workflows, model deployment platforms, disassemblers/decompilers, and malware tradecraft.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)AI lab
Backend/platform engineer supporting AI-powered threat investigation and safety evaluation systems. Responsibilities include designing and maintaining production services for adversarial red teaming workflows, integrating LLM-assisted capabilities for threat analysis, troubleshooting complex investigation systems, and participating in on-call support for critical safety and threat intelligence operations at a frontier AI safety company.
Boston, MA; San Francisco, CA; Seattle, WA; New York City, NY; Washington, DC
Enforcement analyst focused on identifying and investigating harmful or misaligned behavior in autonomous AI agents. Responsibilities include reviewing agent transcripts and tool-use traces, triaging agentic misalignment cases by severity, assessing cyber-related agent activity (scanning, exploitation, credential misuse), making enforcement decisions under usage policy, documenting case findings, and feeding enforcement patterns back to detection and research teams. Requires code reading ability, security/cyber threat intelligence background, and structured investigation experience.
AI Security Engineer role at a global enterprise organization based in Aberdeen. Responsibilities include designing security controls for AI platforms, evaluating generative AI tools (ChatGPT, Claude, Copilot, Gemini) for risks, developing AI governance frameworks, assessing AI-specific threats like prompt injection and model security, conducting threat modeling and security assessments across AI solutions, and embedding security into AI initiatives. Works across information security, IT, data, legal and business teams. Requires strong cybersecurity background with AI/ML security experience, cloud security knowledge (Microsoft/Azure preferred), and familiarity with security frameworks (NIST, ISO 27001, GDPR).
The AI Security Lab invites applications for funded graduate positions in cybersecurity and AI/machine learning. Research focuses on secure and privacy-preserving machine learning, trustworthy generative AI models, and practical security defenses. Successful candidates will contribute to advancing defensive mechanisms for real systems, working on projects supported by NSERC and industry partners. Requires computer science/engineering background with AI/ML or cybersecurity experience, strong programming, and solid mathematics. Prior research publications or open-source contributions are advantageous.
Design, build, deploy, and maintain security controls for enterprise AI platforms and services. Implement technical safeguards for Microsoft Copilot, Azure AI Services, LLM applications, and machine learning solutions. Develop monitoring and detection capabilities for AI misuse, prompt injection attacks, unauthorized access, and sensitive data exposure. Engineer secure implementation patterns for AI application development and model deployment. Automate AI security workflows, integrations, and incident response activities. Support security validation, testing, and continuous improvement of AI security controls across the organization's AI ecosystem.
Drive security research from concept through production, building AI agents that analyze code and cloud infrastructure. Build threat models for AI-native and cloud-native systems, analyze real-world architectures and source code for vulnerabilities, and partner across teams to ship security discoveries. Requires 5+ years security/research experience, AI agent implementation expertise, program analysis foundation, and ability to execute complex multi-quarter projects independently.
Lead evaluation and measurement strategy for agentic AI quality at production scale. Design layered evaluation architectures with automated checks, calibrated LLM-as-judge panels, and expert human review. Build and operate production monitoring systems to detect regressions and drift in AI agents. Conduct adversarial testing and synthetic simulation. Drive human-in-the-loop annotation pipelines to validate fixes. Establish evaluation standards across teams and mentor engineers.
Join the Alignment Red Team at the UK AI Security Institute to research and evaluate misalignment risks in frontier AI systems. Responsibilities include developing automated misalignment detection techniques, building and running alignment evaluations for loss-of-control risks (research sabotage, reward-seeking, deceptive alignment), conducting pre-deployment testing with frontier AI companies, designing evaluation tooling, and contributing to technical publications and reports. Work autonomously on complex research projects involving substantial engineering, ML frameworks, and experiment design. Collaborate with safety teams at frontier labs and advise governments and AI companies on deployment risks. Multiple seniority levels welcome.
Senior role at Trail of Bits focusing on ML assurance and auditing. Responsibilities include researching and developing ML assurance frameworks, conducting risk assessments and threat modeling on ML models and capabilities, analyzing model degradation from systematic defects, reviewing ML system code and architecture with clients, and contributing to policy and regulatory frameworks for AI/ML auditing. Requires 3+ years each in ML development lifecycle, systems/safety/security engineering, and ML performance/safety/security analysis methods. Compensation $175,000–$225,000 base (US W2).
AI Application Security Engineer at Cisco's Enterprise AI team. Secures Generative AI platforms and workloads by embedding security into the development lifecycle. Responsibilities include threat modeling for AI systems, integrating security tooling (SAST, DAST, SCA) into CI/CD pipelines, securing container and Kubernetes environments, protecting inference endpoints, and establishing secure coding standards. Requires 6+ years cybersecurity experience, 3+ years cloud security (GCP/Azure/AWS), and proven experience securing AI/ML workloads and Generative AI systems.
Red team AI-enabled platforms and national security systems. Develop offensive tactics, techniques, and procedures for attacking AI models and their supporting infrastructure. Write exploitation and reconnaissance tools. Conduct vulnerability research on real-world AI systems. Requires penetration testing, reverse engineering, command-and-control framework, and multi-OS security assessment experience.
AI Red Teaming
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)AI lab
Senior Staff Software Engineer designing and building AI-powered security platforms at Cisco. Responsibilities include architecting distributed systems that correlate security telemetry using foundation models for threat detection and prediction, developing AI-enhanced detection workflows, building AIDevOps pipelines for rapid ML experimentation, and designing agentic systems to automate SOC operations. Requires 12+ years experience with security data sources, detection engineering, backend services, and AI model integration. Preferred background includes SOC analyst experience, SIEM architecture familiarity, and hands-on model optimization for security use cases.
Design and build AI-powered threat detection and prediction systems combining security telemetry, detection signals, and foundation models. Develop AI DevOps pipelines for rapid experimentation with data and models. Architect distributed platforms correlating trillions of events into explainable findings and alerts consumed by SOC agents. Integrate RAG/GraphRAG, LLMs, and specialized models (GNNs, GCNs) into real-world security workflows. Collaborate on AI-enhanced threat detection and response operations. Requires 8+ years experience with data platforms, backend services, security telemetry understanding, and model integration expertise.
AI Engineer building agentic systems at SandboxAQ with explicit focus on agent security. Responsibilities include discovery, evaluation, red teaming, monitoring, and guardrails for AI agents. Role combines ML expertise with hands-on security engineering, including frameworks for evaluating agent safety, hardening systems against attacks, and detecting misuse. Requires deep knowledge of AI/ML security, agent orchestration, and hands-on experience with red teaming, jailbreaking, prompt injection, or secure deployment. Hands-on prototyping, testing, and production-ready code delivery across security and safety features for agent systems.
Lead and grow a technical team building secure agentic AI systems. Responsibilities include establishing frameworks for monitoring, guardrailing, and evaluating agents; performing ML tasks like model fine-tuning; red teaming and security evaluation of agents; contributing production-ready code; and translating AI research into applicable security features. Requires deep AI/ML and software engineering expertise with hands-on involvement in security aspects of agent orchestration, jailbreak/prompt injection testing, and detection of AI misuse.
Senior QA Engineer building test infrastructure for AI-agentic Security Operations Center. Develops AI-based solutions and evaluation frameworks for AI agents, workflows, and security systems. Implements LLM-as-judge methodologies, tenant isolation probes, and behavioral regression suites. Requires 8+ years software development and test automation experience, Python/Groovy programming, security compliance framework expertise, and hands-on AI/ML testing with LLM APIs, prompt engineering, and agentic workflows.
Washington, DC (also San Francisco, Santa Monica, Pittsburgh, Boston; remote US available)
Conduct cutting-edge technical research on securing AI systems at RAND's Center on AI, Security, and Technology. Lead complex projects developing AI-specific threat models, building software tools for evaluating AI cyber capabilities, and identifying critical AI security R&D areas. Work spans technical research, infrastructure development, and policy analysis to inform senior government and industry leaders on securing frontier AI models from theft and misuse. Communicate findings through policy briefs and research products to both technical and non-technical audiences. Three-year term appointment.
Engineer building and maintaining agent harnesses and evaluation infrastructure for NVIDIA's AI Safety & Security Engineering team. Responsibilities include designing the agent harness, building systems to run and reproduce security experiments, ensuring reproducibility of vulnerability detection workflows, and collaborating with security researchers. Requires 5+ years of software engineering, strong Python skills, experience with containerized environments, CI/CD, and familiarity with agent frameworks or ML infrastructure.
Set technical vision for exploitability-driven security analysis using AI/ML. Define hardest modeling problems for attack-path probability calibration across environments. Establish engineering standards and AI safety governance for agentic systems in production. Mentor teams, champion AI-native practices, and drive portfolio-wide security scoring architecture. Requires deep production ML expertise (LLMs, foundation models, agentic systems) and applied security depth in threat detection, exposure management, and risk prioritization.
Washington, DC (DC Metro Area); San Francisco, CA; Santa Monica, CA; Pittsburgh, PA; Boston, MA; Remote
Lead research team evaluating AI model security across attack lifecycles including initial access, lateral movement, and defense evasion. Develop benchmarks for autonomous AI operations and assess stealth capabilities. Manage technical personnel and budgets, oversee complex red team projects commissioned by government agencies, and communicate findings through technical analyses and policy briefs. Requires 6+ years security engineering and technical management experience with red team operations background.
San Francisco, CA | New York City, NY | Seattle, WA
Design, build, and operate security controls for reinforcement learning training systems and infrastructure. Work across the full stack (orchestration, environments, training, inference) to identify and fix security problems. Build shared security libraries and tooling for RL engineers and researchers. Implement observability to monitor system behavior. Balance security with training correctness and performance. Strong software engineering in Python and systems languages (Rust, C++, Go) required, with experience in large-scale distributed systems, infrastructure security, Linux/containers/cloud infrastructure, and security fundamentals.
Washington, DC; San Francisco, CA; Santa Monica, CA; Pittsburgh, PA; Boston, MA; Remote (US)
Lead a large portfolio of 15+ researchers conducting technical AI security research, cyber capability evaluation, and infrastructure development at RAND's Center on AI, Security, and Technology. Define research priorities, mentor senior technical staff, oversee AI threat models and security architecture development, and translate technical findings into policy recommendations for government and industry stakeholders. Three-year term appointment with renewal options.
Senior Staff Engineer leading zero-to-one development of a novel exploitability engine that ranks security risks by real-world attack feasibility. Owns end-to-end architecture from evidence ingestion through probabilistic attack-path ranking and validation loops. Establishes AI safety, governance, and guardrails for agentic systems. Responsible for model-shaping decisions on probability calibration, attack-path search, and critical asset definition. Drives technical direction, mentors senior engineers, and partners with security R&D and SecOps to translate customer security problems into architecture decisions.
Own major subsystems of a novel AI-powered exploitability engine that ranks security work by realistic attack paths. Design and deliver core components including probability scoring, exposure graphs, entity resolution, and calibration loops. Establish AI safety and guardrails for agentic components. Work end-to-end from design through production scale, mentoring engineers and partnering with security R&D and SecOps to turn customer security problems into subsystem requirements.
Red Team Security Engineer validates vulnerabilities, configurations, and AI-enabled systems against realistic adversaries using offensive security techniques combined with AI-assisted and agentic methods. Responsibilities include emulating attackers, developing attack paths, testing AI applications for prompt injection and tool abuse, conducting purple-team exercises, and translating findings into defensive improvements across web, cloud, identity, and emerging AI attack surfaces.
Senior security engineer role focused on protecting Amazon's AI/ML services and applications. Responsibilities include security reviews of AI/ML products and technologies, designing secure architectures, implementing secure development lifecycle practices including threat modeling and penetration testing, developing security tools and automation, and mentoring teams. Required experience includes 5+ years in security, system troubleshooting, vulnerability identification, scripting/programming, and code review. Preferred qualifications include threat modeling experience, microservices security knowledge, and AI/ML systems evaluation background.
Technical leadership role directing applied AI strategy for email threat defense systems. Responsibilities include designing ML/LLM/agent-based capabilities for threat investigation and analyst assistance; establishing security safeguards for privacy, prompt injection, tool security, and access control; building evaluation approaches for accuracy, robustness, and false-positive impact; architecting scalable cloud services with strong observability and incident response; threat modeling and security reviews; and mentoring engineers in AI and security engineering disciplines.
Hands-on software engineer at Lenovo's Digital Trust Lab developing and deploying AI security controls across the AI lifecycle. Responsibilities include designing production capabilities for an AI Controls Platform, implementing ML training/fine-tuning pipelines for LLMs, building detection and control mechanisms for data/models/inputs/outputs/agents, and translating AI security research into scalable, robust production controls. Requires 5+ years in software/ML/security engineering with expertise in Python and modern languages, strong CI/CD and testing fundamentals, and preferred knowledge of adversarial ML, LLM security, AI red teaming, and agentic AI security.
Build advanced classifiers and detection systems to identify AI misuse and coordinated harms. Develop monitoring pipelines for production traffic and implement data-driven response systems against malicious actors. Evaluate agentic AI systems through threat modeling and create testing environments for frontier-level attacks. Advance automated red-teaming and adversarial robustness research to systematically uncover vulnerabilities in AI systems.
First-person AI platform architect role building secure LLM infrastructure for regulated financial services. Responsibilities include designing and implementing AI platform governance across Anthropic Claude and OpenAI APIs; securing MCP servers and agent gateways; building data privacy and security architecture with prompt classification and output controls for FCA/DORA compliance; deploying secrets and credential management with least-privilege IAM; and implementing observability across token consumption, cost, and policy violations. Requires 8+ years engineering with 2+ years production LLM systems, hands-on Python, AWS/GCP cloud security, and fluency in LLM threat surfaces including prompt injection and model supply-chain risks.
Full-time remote role designing and operating security controls for AI workloads. Responsibilities include designing detection capabilities for AI-specific threats, engineering automated response playbooks, implementing security controls across AI development platforms, securing model training environments, and conducting technical risk assessments. Requires 5+ years in cybersecurity or AI/ML systems, expertise in AI/ML security and cloud security, Python proficiency, and knowledge of MITRE ATLAS and OWASP AI Top 10.
Detection & Response
LLM Security
MLSecOps
Employer not disclosed in listing snippet (posted via Virtual Vocations)Security vendor
Research and develop AI safety solutions for large language models and AI agents at Huawei. Design tools for content moderation, runtime monitoring, and violation detection. Focus on adversarial robustness, jailbreaking defenses, safety alignment, and data privacy. Collaborate with academic institutions and contribute to AI safety standardization. Provide technical governance on security protocols and privacy frameworks.
Offensive AI security researcher building autonomous agents to find and exploit vulnerabilities in AI systems and infrastructure. Responsibilities include designing AI-driven attack workflows, conducting jailbreaks and prompt-injection attacks, red teaming AI products, assessing Model Context Protocol systems, and researching security weaknesses in models. Translate findings into engineering requirements and collaborate with teams to implement mitigations. Requires 2–7 years offensive cybersecurity experience, published CVEs, hands-on jailbreak expertise, and ability to use AI models and agents in attack scenarios.
Develop LLM workflows and AI agents to process unstructured intelligence and analyze adversary behaviors for Akamai's threat intelligence platform. Conduct vulnerability assessments, research emerging attack techniques, and create security tools. Produce and present intelligence to internal teams and the security community. Collaborate with architects and engineers to enhance system resilience against adversarial threats.
Staff-level researcher responsible for setting AI security research agenda, building autonomous agents to hunt vulnerabilities in AI systems, conducting offensive security testing including jailbreaks and prompt-injection attacks against AI models, discovering exploitable issues in AI infrastructure, and establishing security controls and guardrails. Must translate research findings into engineering requirements and influence cross-team implementation of fixes.
Staff Security Engineer responsible for architecting modern detection systems and AI-assisted SecOps workflows across cloud infrastructure, identity, and application ecosystems. Establishes detection coverage for AI and agentic threat vectors including prompt injection and tool misuse. Designs and deploys AI-assisted investigation workflows using LLMs and automated agents for triage and threat containment. Leads defensive testing and adversarial validation exercises to evaluate detection resilience against AI-driven threats. Requires 8+ years detection engineering/incident response experience with practical AI tooling integration, strong automation skills, and cloud security expertise.
Staff-level security engineer building AI-powered security automation and tooling at ServiceNow. Designs and develops security capabilities for enterprise-scale systems, including AI agent security tools in collaboration with the AI Security Research team. Contributes code to product engineering codebases and develops internal security platforms leveraging ServiceNow's runtime, ACL enforcement, and workflow engine. Founding team member shaping engineering practices and technical standards for a new Security R&D organization focused on production-grade security capabilities.
Build and extend LLM-based red team agents that perform autonomous reconnaissance, exploitation, and evidence capture against NVIDIA targets. Responsibilities include designing multi-agent orchestration systems, encoding real attack tradecraft into prompts and tools, building exploit-confirmation harnesses to reduce false positives, engineering safety controls for autonomous offensive operations, and evaluating frontier models for offensive security tasks. Role requires deep hands-on exploitation expertise across web applications, cloud/Kubernetes, or systems, combined with practical LLM agent framework experience and sound judgment about autonomous offensive tooling scope and authorization.
Build and own the security platform that discovers, scans, triages, and routes security findings. Design and operate services in Go and Python on Kubernetes and AWS. Develop agentic workflows (Claude Code skills, CI review agents, automated triage and verification) that multiply team capacity. Own the event-driven NATS bus connecting security services. Implement and tune CI security gates (SAST, SCA, secret detection, container and IaC scanning). Build automation for triage-to-remediation loops with finding validation and fix guidance. Participate in threat modeling and on-call rotation.
Secures AI agent systems at ServiceNow by analyzing security of agentic architectures, designing controls for context handling and tool-calling loops, detecting adversarial subversion, building runtime policy enforcement and behavioral detection systems, threat modeling new AI features, red-teaming agent defenses against prompt injection and tool abuse, and creating repeatable security evaluations. Partners with engineering to ship hardened controls and advises product teams on secure AI design.
Design, build, and implement tools for AI security testing, penetration testing, red teaming, and vulnerability assessment. Assess AI-powered applications and third-party AI technologies for security risks. Develop security requirements and best practices for AI systems including Generative AI, RAG, and agentic systems. Integrate security testing into CI/CD pipelines. Requires 5+ years software development, Python expertise, application security knowledge, and understanding of modern AI architectures and LLM-specific attack vectors.
Senior-level detection and response engineer responsible for SIEM/XDR maturity, detection rule development, incident investigation, and vulnerability management. Will build and operate agentic workflows for alert triage, threat hunting, and incident investigation to scale security operations. Requires 6+ years in security/infrastructure engineering with hands-on SIEM, vulnerability management, cloud security (AWS/Kubernetes), and active AI tooling experience. Leads detection strategy, audit coverage, incident response, and proactive threat hunts across cloud and identity planes.
Senior security engineer solving difficult security problems across Microsoft AI's production infrastructure. Build end-to-end security solutions including automated controls, identity and secrets hardening, detection systems, adversarial testing, and AI-assisted security capabilities. Responsibilities span application security, platform security, cloud infrastructure, data protection, security telemetry, detection and response, and incident readiness. Own security problems from discovery through design, implementation, deployment, and validation. Work directly with product, research, platform, and infrastructure teams. Use AI routinely for research, coding, analysis, testing, and investigation while maintaining engineering judgment and accountability.
AI Security Engineer at GuidePoint Security focused on securing generative AI and agentic systems. Core responsibilities include threat modeling for AI workloads, security architecture assessment of LLMs and GenAI pipelines, secure integration of cloud AI services, data security for RAG architectures and vector databases, and development of AI security roadmaps and controls frameworks. Requires 5+ years security engineering experience with hands-on agentic AI implementation, proficiency in Python, deep LLM and agentic AI knowledge, and understanding of AI-specific attacks including prompt injection and data poisoning. Collaborates across AppSec, cloud security, and operations teams to deliver holistic AI security solutions.
Join Apollo Research's Infra & Security team to identify, research, and remediate threats introduced by AI agents and conventional security risks. Responsibilities include red-teaming agent sandboxes and internal infrastructure, developing threat models for coding agents with privileged access, tracking adversary tactics relevant to AI systems, designing novel security solutions where no playbook exists, and owning findings through to deployed fixes including detection rules and control systems. Requires 5+ years hands-on security experience, offensive security background, and ability to translate security findings into engineered solutions at startup pace.
Cincinnati, Ohio / Livonia, Michigan, United States
Siemens seeks an AI Security Engineer to implement security controls across the AI/ML lifecycle. Responsibilities include securing model pipelines and CI/CD for MLOps, establishing cryptographic mechanisms for data provenance verification, conducting AI vulnerability testing and threat modeling against AI-specific attacks (prompt injection, model poisoning, model inversion), performing AI impact assessments and bias audits, and maintaining data provenance documentation and data bill of materials. Requires deep understanding of end-to-end ML lifecycle from data ingestion through production inference, with hands-on experience in data lineage tools and MLOps security.
Design and build benchmarking, evaluation, and reproducibility infrastructure for NVIDIA's AI Safety & Security Engineering program. Define metrics and protocols for measuring AI-powered vulnerability detection and remediation tooling. Ensure traceability and evidence discipline across security evaluation runs, working with researchers to design experiments that validate security capabilities. Own how the program measures real security progress versus anecdote.
Lead AI Security Engineer responsible for safety evaluation and security testing of LLM deployments and agentic AI systems. Design and execute red-teaming, jailbreak testing, prompt injection testing, and security verification for AI agents. Build threat models covering user input through model reasoning to tool execution. Scope and review external red-team/pentest vendors. Track emerging frameworks (OWASP Top 10 for LLM/Agentic Applications, NIST AI Risk Management Framework, ISO/IEC 42001, EU AI Act) and translate research into test requirements. Partner with AI/ML teams on secure-by-design practices. Build adversarial-prompt harnesses, automated jailbreak pipelines, and tool-schema fuzzers. Mentor engineers on safe and secure AI system design.
Design and build evaluation harnesses and datasets to measure risks posed by frontier AI systems, including testing for dangerous capabilities such as security vulnerability exploitation. Collaborate with government and industry partners to scope evaluations, conduct technical research on agent robustness and AI control protocols, and publish evaluation methodologies and technical reports for policymakers. Requires 3+ years addressing sophisticated ML problems, practical ML pipeline building, and experience in red-teaming or adversarial testing of AI systems.
Pioneering AI security researcher role at early-stage AI-security startup. Responsibilities include advanced threat modeling for AI systems, designing red team scenarios (prompt injection, jailbreaking, model manipulation), building proof-of-concept exploits demonstrating vulnerabilities, and shaping industry security standards. Candidates should have 0-10+ years security research experience, demonstrated bug bounty skills, deep application security knowledge, and passion for AI safety. Focus on developing proprietary attack frameworks and publishing industry-defining research to establish gold standards for AI security practices protecting AI interactions at scale.
AI Red Teaming
LLM Security
Security Research
CareerXperts (client AI security startup)Security vendor
Research Engineer/Scientist position with the AI Security Institute's Alignment Red Team. Conducts misalignment research on frontier AI systems across safety, security, and alignment domains. Develops evaluation methodologies, publishes findings, and builds tools to advance model alignment and reliability. Works with frontier labs and government partners. Open to junior through principal levels.
Remote, Canada; Remote, Israel; Remote, United Kingdom; Remote, United States
Staff Backend Engineer leading technical direction for GitLab's SAST (static application security testing) engine. Owns architecture for program analysis including parsing, symbol resolution, call graphs, and taint/data-flow analysis across multiple languages. Designs and maintains guardrails for AI agents that implement and review code changes. Builds evaluation tooling to validate detection quality against benchmark applications with known vulnerabilities. Mentors engineers, sets team technical standards, and ensures agent-generated code meets security and performance requirements through independent review panels, mutation testing, and CI gates.
Principal ML Engineer leading production AI systems with focus on AI governance and security. Responsibilities include deploying and optimizing models at scale, designing distributed microservices architectures, implementing agent permission structures and prompt injection defenses, enforcing data isolation boundaries, threat modeling, and building human-in-the-loop workflows. Requires 12-15+ years software engineering experience with evolution to production ML, expertise in MLOps, RAG, vector search, distributed systems, and hands-on AI security practices.
Research Engineer/Research Scientist role at the AI Security Institute focused on the Alignment Red Team. Responsibilities include researching methods to detect misalignment in frontier AI models, building and running alignment evaluations for loss-of-control risks, conducting pre-deployment testing, and designing software tooling for evaluations. Work involves threat modeling, analyzing model behaviors, incident investigation, and publishing research. Requires substantial AI safety/security research experience with engineering, strong ML and Python software engineering skills, and experience with LLMs and evaluation frameworks.
Build telemetry, logging, and SIEM pipelines for detection and response across multi-cloud infrastructure. Deploy osquery and eBPF sensors at fleet scale, automate incident response (host isolation, credential revocation, evidence collection), and test AI/agent automation for security operations. Operate AWS infrastructure, manage EDR and endpoint security, join on-call SOC rotation, and automate evidence collection for compliance audits. Requires 5+ years in security/infrastructure, production code in Go/Rust, fleet-scale sensor deployment, AWS operations, and SIEM pipeline experience.
Lead detection and response capabilities for AI model threats at Anthropic. Build and deploy tooling, including LLM-based tools, to detect and respond to incidents spanning all layers of the technology stack. Create detections, playbooks, and workflows for threat identification and response. Handle security incidents from external attacks to insider threats. Conduct incident investigations, collaborate with security and engineering teams, and participate in on-call rotation. Requires incident response experience, proficiency with EDR/SIEM/SOAR tools, cloud operations knowledge, Python/SQL skills, and 7+ years in security engineering or detection/response roles.
Fullstack engineer on Anthropic's Safeguards team building systems to detect unwanted model behaviors and prevent model misuse. Design internal review tools for abuse investigation, interfaces for human supervision of AI agents, and visualization tools to surface abuse patterns. Own frontend architecture for sensitive data handling at scale, including performance optimization and access controls. This role combines AI safety oversight with hands-on security engineering for model abuse detection and mitigation.
AI security researcher at Roke focused on researching emerging AI threats, vulnerabilities, and attack techniques. Responsibilities include designing and developing security solutions and prototypes, performing vulnerability analysis and reverse engineering across platforms, and collaborating with multidisciplinary teams to transition research into real-world capabilities. Role requires strong technical background in exploit development, secure software development, or vulnerability research combined with understanding of ML ecosystems and AI security risks.
AI Red Teaming
MLSecOps
Security Research
Roke (via Sanderson Government and Defence)Government
Application Security Engineer supporting secure software development lifecycle programs, DevSecOps automation, and security assessments of AI-enabled and agentic applications. Responsibilities include running and tuning SAST/DAST/SCA tools, designing CI/CD pipeline security integrations, performing threat modeling and architecture reviews, assessing software supply chain controls, and advising on secure adoption of AI coding assistants. Hands-on work with secure code review, vulnerability remediation guidance, and building agentic workflows to scale security testing and auto-remediation. Supports clients in maturing AppSec programs aligned to OWASP SAMM, BSIMM, and NIST SSDF frameworks.
Design and build cyber ranges, CTF-style challenges, and agentic scaffolding to evaluate frontier AI models' cybersecurity capabilities. Conduct pre-deployment testing of advanced models on multi-step network intrusions, vulnerability exploitation, and autonomous technical tasks. Engineer realistic evaluation environments, develop scoring methodologies, and contribute to UK government assessments of AI cyber risks.
AI Red Teaming
Detection & Response
MLSecOps
AI Security Institute (UK AI Safety Institute)Government
Freelance specialist role designing adversarial prompts and creative inputs to test generative AI systems including LLMs, text-to-image, text-to-video, and multimodal models. Identify and document model weaknesses, categorize vulnerabilities, and produce structured security findings. Work spans adversarial analysis and creative prompt design across multiple languages and policy domains including hate speech, harm, and terrorism. Support data annotation and safety curation processes.
San Francisco, CA, USA; Mountain View, CA, USA; New York, NY, USA
Build solutions to protect frontier AI models from misuse and cyber attacks. Improve adversarial evaluation and auto-red teaming techniques, develop out-of-model defenses such as classifiers and introspection probes, and enhance Gemini's cyber defense capabilities. Apply engineering, ML, RL, and cybersecurity knowledge to secure models and build scalable infrastructure. Work as a Tech Lead Manager on the cyberattack safety team, translating research to production impact.
Develop processes and infrastructure for machine learning red team exercises targeting ML deployments. Plan and execute realistic red team exercises simulating attacker tactics against production ML systems. Design tools, controls, and defensive improvements in cooperation with product security teams. Document findings for technical and executive audiences. Requires 5+ years in security engineering, computer/network security, and threat modeling.
Design and implement continuous security monitoring for SaaS, cloud, and endpoint environments. Build integrations across security platforms using APIs and automation. Create agents and workflows to automate remediation and risk detection. Monitor AI models, agents, and MCP usage in production. Translate security requirements into measurable monitoring controls and dashboards. Mentor engineers and lead complex technical initiatives from discovery through implementation.
Build and deploy AI agents that function as autonomous security researchers and first responders. Design LLM-based agents for automated vulnerability research, code analysis, and security patch generation. Develop self-healing CI/CD pipelines that automatically test and deploy security patches. Implement AI-driven threat detection to identify anomalous traffic and autonomously update WAF rules. Integrate security scanning tools with AI agents to prioritize and resolve alerts without manual triage. Move security posture from human-in-the-loop to human-on-the-loop automation.
Design and build the enterprise AI agent platform at NVIDIA, focusing on runtime safety harness, policy enforcement, agent orchestration, credential management, and observability. Responsibilities include building policy engines for agent action validation, approval gates and kill switches, multi-agent orchestration with secure credential brokering, and evaluation loops to improve agent behavior. Requires 12+ years distributed systems experience, hands-on agent harness experience, and applied security fundamentals including threat modeling, authorization, and secrets management.
Develop and deploy safety solutions for large language models and autonomous AI systems. Focus on LLM security (backdoors, data poisoning, latent behaviors), frontier risks (deception, manipulation), and agentic safety for multi-turn tool-calling systems. Create datasets, evaluation methodologies, and training recipes across safety tracks. Research novel approaches like instruction hierarchy and risk detection. Collaborate cross-functionally to scale LLM security and safety techniques across NVIDIA's frontier models.
GuidePoint Security seeks an AI Security Engineer to design, implement, and secure generative AI solutions for enterprise clients. Responsibilities include conducting AI platform security assessments, threat modeling for AI workloads (prompt injection, data poisoning, supply chain risks), evaluating LLM and agentic coding tools, assessing data security controls in RAG architectures, performing shadow AI discovery, developing agentic workflows, and delivering security architecture reviews. Requires 3+ years security engineering experience with cloud/application security focus and hands-on experience with enterprise AI platforms (Claude, ChatGPT, Copilot), cloud AI services (AWS Bedrock, Azure AI), and understanding of AI-specific threats.
Bellevue, Washington, US; Menlo Park, California, US; New York, New York, US; Remote, US
Security engineer at Meta's Central Security team focused on AI security and native-code security. Responsible for identifying vulnerabilities in AI systems before attackers exploit them, building solutions to eliminate security weaknesses, and providing expert guidance to engineering and product teams on AI security best practices. Works to protect Meta's AI-driven products and services used by billions of people.
Member of Technical Staff, Security Engineering at METR, a nonprofit focused on AI capabilities and risk assessment. Responsibilities include offensive security and automated AI red teaming, building AI systems for threat detection and response, detection engineering and incident response across cloud infrastructure and endpoints, and securing evaluation infrastructure that executes frontier AI agents. Required expertise spans systems/cloud/identity security, offensive security (red teaming, penetration testing), and AI/LLM engineering with AWS proficiency.
Design and operate a secure cyber-range platform to evaluate AI agents and frontier models in cybersecurity. Develop red-team and blue-team configurations, validate cyber-defence scenarios, manage secure import and isolation of third-party environments, and integrate agentic AI capabilities for vulnerability identification, exploitation verification, and remediation. Support EU cybersecurity and AI policy through scientific contributions.
AI Red Teaming
MLSecOps
Security Research
European Commission Joint Research CentreGovernment
Senior Manager leading NVIDIA's AI Safety & Security Engineering team from inception. Responsibilities include hiring and coaching founding engineers across harness/platform engineering and security research; delivering the Find, Validate, and Patch engineering roadmap; and collaborating with evaluation and security leadership. Requires 12+ years software engineering experience with 5+ years managing complex systems teams (distributed infrastructure, ML platforms, security tooling). The role combines AI/ML systems expertise with vulnerability research and security program exposure to build tooling that identifies and patches software vulnerabilities using AI-powered approaches.
Lead strategic agentic AI partnerships for enterprise ISVs, designing and deploying secure multi-agent systems with guardrails, runtime security, and confidential computing. Architect threat-detection and incident-response agent workflows, integrate LLM safety models, and conduct adversarial testing and red-teaming. Build production-grade secure AI infrastructure, create reference architectures, and provide technical guidance on prompt-injection defense, tool-based exfiltration prevention, supply-chain security, and GPU-accelerated safety workflows.
Conduct structured adversarial testing on ByteDance's generative AI products and models to uncover emerging risks. Investigate jailbreaks, evasions, prompt-based attacks, and other adversarial techniques to identify model failure modes, stress-test safeguards, and assess AI safety vulnerabilities across modalities. Document findings with severity assessments and mitigation recommendations; partner with policy, product, and engineering teams on risk closure and evaluation strategy.
Design and enforce security architecture for IONOS's internally-operated AI platforms, agents, and infrastructure. Responsibilities include establishing security standards for AI model gateways, agent frameworks, and retrieval pipelines; managing non-human identity and privileged access for agents; conducting pre-deployment security assessments; and addressing AI-specific threats such as prompt injection and data exposure. Also oversees infrastructure security including virtualization, container platforms, and tenant isolation across multi-brand environments.
Principal Security Research Engineer on the Threat Research and Detection Engineering (TRaDE) team at Elastic. Design and execute security tests for GenAI applications, agentic systems, and LLM-backed products, focusing on prompt injection, indirect injection, retrieval poisoning, tool misuse, and sensitive data extraction. Investigate multi-domain threat vectors in AI systems, translate findings into detection rules and protections, and develop AI-assisted workflows to enhance detection capabilities. Requires hands-on experience with LLM tools, detection engineering, threat research, and knowledge of AI testing frameworks.
Lead software security architecture across Cisco's AI-driven platforms, focusing on autonomous agent and LLM application security. Design trust boundaries, sandboxing, and execution guardrails for agentic workflows. Architect secure Model Context Protocol (MCP) integrations with granular authentication and authorization. Mitigate AI threat vectors including prompt injection, tool hijacking, and context leakage. Establish spec-driven security standards, implement automated security contract testing, and lead threat modeling for multi-tenant distributed systems. Mentor senior engineers on zero-trust application design and secure-by-default patterns. Serve as principal escalation point for critical application security reviews and vulnerability disclosures.
NIST's CAISI Agent Security team seeks research engineers and scientists to conduct cutting-edge security research, assess AI agent vulnerabilities and robustness, and develop agent security best practices and guidelines.
Research Scientist focused on proactive threat mitigation, adversarial machine learning, and agentic security. Develops foundational ML research in model robustness, continual learning, and interpretability to advance trustworthy AI. Designs rigorous evaluation protocols, scenario-based benchmarks, and stress-testing methodologies for frontier AI capabilities. Collaborates with engineering teams and academic partners to transition research into production AI safety solutions. Expertise required in adversarial ML, AI agent security, data poisoning, prompt injection, model backdoor detection, and red-teaming frontier AI systems.
Lead design and implementation of responsible AI frameworks, safety guardrails, and governance for GenAI systems. Own AI safety evaluation pipelines including red-teaming, adversarial robustness testing, jailbreak and prompt injection assessments. Develop explainability tooling for model audits and regulatory reviews. Partner with security, risk, and compliance teams on safety requirements. Lead incident response and root cause analysis for AI safety issues. Mentor engineers on AI safety practices.
Build frontier AI-powered offensive security capabilities at a public IoT platform company. Conduct AI-driven vulnerability assessments of cloud, software, and firmware systems using large language models and agentic workflows. Red-team LLM-integrated systems for prompt injection and agent abuse vulnerabilities. Benchmark frontier models for security tasks and establish adoption guardrails. Develop novel AI-enabled security tooling, pressure-test workflows, and drive org-wide adoption. Support application security triage and bug bounty programs. Partner with engineering and leadership to shape Samsara's AI security strategy. Requires 8+ years in AppSec/offensive security plus hands-on experience building AI/agentic security solutions.
Senior security engineer responsible for cloud product and infrastructure security, conducting security assessments and penetration testing. Researches offensive and defensive technologies, discovers and defends against vulnerabilities, manages configuration risks, and applies AI techniques to improve attack and defense capabilities. Requires programming proficiency and in-depth knowledge of AI security, devsecops, or related security domains.
Research cloud attack techniques and evasions against detection sensors across Windows, Linux, and macOS. Conduct attack path analysis, build detection tools, create proofs of concept, and collaborate with threat intelligence and detection engineering teams to identify gaps and improve detection capabilities. Requires 4+ years in red teaming/security research, expertise in cloud platforms (AWS, GCP, Azure), OS internals, Python/C++, EDR internals, and experience with agentic AI workflows for detection engineering.
Red team real-world AI-enabled systems (both model and supporting infrastructure) in national security contexts. Develop tactics, techniques, and procedures for attacking AI systems. Write tools in Python, PowerShell, C, and BASH to support red team operations. Requires BS/MS/PhD in computer science or related field with 2–8 years of experience, strong offensive cyber skills (penetration testing, C2 frameworks like Cobalt Strike, reverse engineering, exploit development), TCP/IP mastery, and hands-on Linux/Windows security assessment experience.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)Government
Research Scientist role at Meta focused on advancing AI safety and security through system design and modeling. Responsibilities include designing, developing, and evaluating novel approaches to ensure AI systems are safe, secure, and aligned with human values. Works in a focused incubation team collaborating with scientists and engineers across the organization.
Join Carnegie Mellon's SEI CERT Division to conduct pioneering research in AI security. Responsibilities include developing approaches for analyzing robustness of AI systems, discovering vulnerabilities, reverse engineering AI systems, evaluating defense effectiveness, and influencing AI security strategy. Work with elite professionals and government sponsors to build methodologies addressing emerging threats to AI systems. Requires BS with 8 years, MS with 5 years, or PhD with 2 years in ML, cybersecurity, or related fields, plus practical vulnerability research experience and proficiency with AI/ML frameworks and reverse engineering tools.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)AI lab
Develop machine learning-based prototypes, tools, and systems for AI security applications. Collaborate with researchers to design and execute experimental AI security solutions. Support AI red teaming and adversarial machine learning initiatives. Process and analyze cybersecurity datasets. Apply software engineering best practices to build scalable systems that help solve AI security challenges and influence national AI and cyber security strategy.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)AI lab
Research role at Carnegie Mellon's Software Engineering Institute (CERT Division) focused on AI security. Responsibilities include vulnerability discovery in AI systems, reverse engineering models, evaluating robustness of defenses, analyzing threats to AI systems, and developing methodologies to characterize vulnerabilities. Requires BS in ML, cybersecurity, or related field plus practical experience in vulnerability research and AI/ML implementation. Will develop tools, datasets, and publish findings for government and industry stakeholders.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)AI lab
Join Carnegie Mellon University's Software Engineering Institute (SEI) CERT Division to conduct pioneering AI security research. Develop state-of-the-art approaches for analyzing robustness and vulnerabilities in AI systems. Responsibilities include reverse engineering malicious AI code, vulnerability discovery and assessments, evaluating defense effectiveness, identifying emerging threats, and publishing research findings. Work with government sponsors, industry partners, and policymakers to influence national AI security strategy. Requires BS in ML/cybersecurity with 3 years experience or MS with 1 year experience, practical vulnerability research background, AI/ML implementation skills, and familiarity with reverse engineering tools and Python/C++.
MLSecOps
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)AI lab
Red team AI-enabled systems and develop attack tactics against AI platforms in national security contexts. Assess both AI models and underlying hardware/software/network infrastructure. Develop tools and techniques to identify vulnerabilities in AI systems and prepare defenders for real-world threats. Requires offensive cyber expertise combined with AI security knowledge, hands-on penetration testing, exploit development, reverse engineering, and scripting in Python, C, BASH, and PowerShell.
AI Red Teaming
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)Government
Senior researcher role at Carnegie Mellon's Software Engineering Institute focused on advancing state-of-the-art AI security. Responsibilities include developing approaches for analyzing AI system robustness, discovering and assessing vulnerabilities in AI systems, reverse engineering malicious AI code, evaluating defenses and mitigations, and publishing research findings. Requires 5-10 years experience combining AI/ML and cybersecurity expertise, proficiency with ML frameworks and reverse engineering tools, and ability to influence national AI security strategy.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)AI lab
Senior role at CMU's CERT Division developing ML-based prototypes, tools, and systems for AI security applications. Responsibilities include AI red teaming, adversarial ML research, security analysis of AI systems, and translating research concepts into operational capabilities. Work involves processing cybersecurity datasets, designing experimental AI security solutions, and collaborating with researchers to build technologies addressing national AI security strategy.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)AI lab
Conduct research on vulnerabilities and defenses for AI/ML algorithms within Carnegie Mellon's Secure AI Lab. Lead investigations into threat models targeting AI systems, design adversarial attacks and mitigations, and transition research capabilities to government sponsors. Responsibilities include identifying emerging AI vulnerabilities, performing original research on adversarial ML, developing prototype defenses, and mentoring junior researchers.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University – Software Engineering Institute (SEI)AI lab
Machine Learning Engineer at Gray Swan AI focused on developing adversarial testing methodologies, model evaluation frameworks, and robust inference systems for AI safety. Responsibilities include designing and deploying ML models for threat detection and red teaming agents, advancing monitoring and control methodologies for production models, and translating novel AI-safety research into scalable systems. Work spans applied research and production system building at the intersection of AI security and deep learning, with emphasis on robustness testing and adversarial resilience.
Senior technical leader designing, implementing, and operating security controls for enterprise AI systems, generative AI solutions, LLMs, AI agents, and machine learning platforms. Develops reusable security patterns, guardrails, and automation across AI technology stacks. Partners with AI engineering and data teams to embed security throughout the AI delivery lifecycle. Performs adversarial testing, implements detection capabilities for AI security events, and assesses AI supply chain risks. Requires 7-9 years cybersecurity experience with minimum 4 years in security roles, expert knowledge of AI/cloud security, and hands-on experience securing enterprise AI platforms, copilots, and model providers.
Lead AI security controls design, implementation, and operation for a Canadian financial institution. Embed security into AI platforms, generative AI solutions, AI agents, and machine learning environments across the enterprise. Develop reusable security guardrails, perform adversarial testing, implement detection capabilities for AI security events, and provide technical guidance on secure AI adoption. Work with AI Centre of Enablement, engineering, and data teams to protect against data leakage, model misuse, insecure integrations, and unapproved AI use. Requires 7-9 years security/engineering experience (minimum 4 in cyber security) with expert-level knowledge of AI, cloud security, and AI-specific risks including prompt injection, data poisoning, and supply chain threats.
Staff-level security researcher combining attacker's perspective with ML/LLM-driven detection development. Responsible for researching APT techniques and TTPs, designing end-to-end AI-powered detection pipelines that analyze fleet-wide EDR telemetry from millions of endpoints, developing LLM-based agents to automate detection authoring, and maintaining production detections. Requires 5+ years security research/threat hunting, deep Windows internals knowledge, Python development, SQL/KQL expertise, and hands-on ML/LLM application to security detection.
Lead a team of engineers building behavioral detection and prevention capabilities for Windows endpoints using machine learning, low-level telemetry, and attack simulations. Own design and delivery of detection engines protecting tens of millions of endpoints in SentinelOne's AI-native endpoint protection platform. Responsibilities include hiring and leading the team, owning detection roadmap and quality metrics, building attack tools and PoCs to validate detections, and staying hands-on with code and detection design. Requires 5+ years in detection engineering, EDR/AV development, malware analysis, or offensive security; deep Windows internals knowledge; and experience measuring behavioral detection efficacy.
Security architect for autonomous AI agent platform in government sector. Responsibilities include designing security guardrails for AI agents, threat modeling agentic workflows, building audit trails and explainability mechanisms, implementing data governance controls, and conducting proactive security testing to identify vulnerabilities in AI instruction processing and tool usage. Requires 6–10 years cybersecurity experience with 2–3 years focused on AI/ML or LLM security, with expertise in agentic systems, prompt injection risks, and cloud-native security.
Remote - Dallas (US, except SF Bay, NYC, DC metro areas)
Senior Threat Detection Engineer at Samsara responsible for building, deploying, and improving MITRE ATT&CK-aligned detections across cloud, endpoint, identity, email, and application telemetry. Owns full detection lifecycle from hypothesis and data validation through deployment and retirement. Advances detection-as-code platform through version control, peer review, automated testing, and CI/CD. Evaluates AI-powered security capabilities including LLM agents and MCP integrations for security risks. Partners with Security Operations on incidents and threat hunting. Requires 6+ years in detection engineering, strong Python/SQL, SIEM expertise, AWS/Linux/EDR knowledge, and understanding of AI/LLM security risks and failure modes.
Security Researcher for Microsoft's AI Red Team discovering and exploiting GenAI security vulnerabilities in frontier and foundational models. Responsibilities include end-to-end assessment of AI systems, developing red teaming methodologies and techniques, managing stakeholder communication, and collaborating with offensive security engineers and adversarial ML experts. Work covers Microsoft's AI portfolio including Copilot products. Requires cybersecurity background with penetration testing or vulnerability research experience; familiarity with agents testing and AI systems preferred. Bachelor's degree in relevant field plus 2+ years experience, or Master's plus 1+ years, or equivalent.
Design, implement, and operate offensive cyber-capability evaluations for frontier AI models and agentic systems. Build realistic evaluation tasks covering vulnerability analysis, exploit development, and multi-step offensive workflows. Execute controlled experiments with AI models, analyze behavior to distinguish genuine capability from evaluation artifacts, and develop cyber ranges with appropriate security controls. Requires offensive security experience combined with AI/model evaluation expertise and programming proficiency.
Senior technical leader building the engineering and execution engine for FAR.AI's frontier AI red-teaming program. Responsibilities include designing scalable red-teaming tools and agentic systems, managing vulnerability assessment workflows, leading high-stakes pre-deployment testing engagements with frontier AI companies and governments, and building an elite engineering team. Focus areas: automated attack simulation, harmfulness evaluation, internal tooling for systematic model testing, and scaling red-teaming operations across closed and open-weight AI systems.
Penetration tester joining Bosch's AI Safety & Security team to execute structured security and safety evaluations against LLM deployments, agentic AI systems, and tool-calling integrations. Responsibilities include running red-teaming and jailbreak tests, testing for prompt injection and excessive agency in AI agents, verifying guardrail controls under adversarial conditions, building adversarial test tooling and scripts, tracking published AI security research, and coordinating findings with AI/ML engineering teams. Individual-contributor role executing real engagements from day one.
Lead design and implementation of Microsoft's AI observability, detection, investigation, and hunting platform. Build large-scale distributed data systems for AI security monitoring, attack reconstruction, and threat detection across Microsoft's AI estate. Design detection infrastructure for attack signatures, behavioral anomalies, and model-assisted analysis. Develop high-volume data integrations and correlation pipelines using Spark, Kusto, and streaming platforms. Mentor engineers and drive security architecture reviews. Requires 6+ years distributed systems/security engineering and 2+ years modern AI systems experience (copilots, agents, LLMs, RAG).
New York, NY, USA; Mountain View, CA, USA; London, UK
Research Scientist at DeepMind focused on safety and behavior of Gemini models. Responsibilities include driving innovation in safety/security jailbreak detection and mitigation, developing red and blue teaming methods for GenAI models, exploring data and algorithmic solutions for model safety, improving adversarial robustness with focus on agentic abuse risks, and executing experimental plans. Requires PhD in Computer Science or equivalent and 2+ years LLM safety/security experience. Preferred qualifications include agentic workflows, synthetic data generation, and research-to-product experience.
New York, NY, USA; Mountain View, CA, USA; London, UK
Research Scientist role at Google DeepMind focused on advancing safety and security of Gemini foundation models. Responsibilities include developing red and blue teaming methods for text, multimodal, and agentic GenAI systems; investigating and mitigating safety/security jailbreaks; exploring algorithmic solutions to address adversarial risks; and executing experimental plans to enhance model robustness. Requires PhD and 2+ years LLM safety/security experience. Preferred: agentic workflows, synthetic data generation, evaluation pipelines, and publication track record.
Design and maintain security controls across the AI/ML lifecycle, including safety research and model internals inspection to detect hidden deception or unwanted concepts. Conduct threat modeling and security assessments for AI/ML systems (data poisoning, model evasion, adversarial inputs). Design security guardrails and boundary mechanisms for LLMs and SLMs. Develop reference architectures for AI deployments including agentic workflows. Build AI-driven tooling to strengthen cybersecurity posture. Drive SSDLC and DevSecOps practices for AI products. Requires 5+ years information security, 1-2 years AI/ML security, proficiency in Python/Go, and frameworks like PyTorch and interpretability tools.
Senior-level position at Samsara combining application security with frontier AI. Responsibilities include using AI/LLM tools for offensive vulnerability assessment and red-teaming, evaluating new AI models for security use, building AI-enabled security tooling, conducting technical assessments across software and firmware, and developing organization-wide AI security strategy. Requires 8+ years in application security, hands-on AI/agentic workflow development, experience with AI-specific attack techniques, and ability to secure and validate agentic AI systems, RAG systems, and LLM-integrated platforms.
San Francisco, CA | New York City, NY | Seattle, WA
Software engineer building safety and oversight mechanisms for AI systems. Responsibilities include developing monitoring systems to detect unwanted model behaviors, building abuse detection infrastructure, surfacing abuse patterns to research teams for model hardening, and creating multi-layered real-time defenses against adversarial inputs and misuse of AI models at scale.
Lead security engineering across authentication, identity, and access control platforms powering AI companies. Responsibilities include secure design partnerships, penetration testing, code audits, vulnerability assessment, security tooling integration, and production remediation. 5+ years security engineering experience required. Strong coding ability and AI/ML familiarity preferred. Focus on securing enterprise-ready AI agent authentication and access control systems.
Security Operations engineer focused on AI/ML system security. Responsibilities include developing and maintaining AI-specific incident response playbooks (prompt injection, model poisoning, adversarial attacks), monitoring generative AI systems and LLMs, engineering detection logic for AI security threats, analyzing security implications of new AI/ML platforms before production deployment, reviewing model robustness and adversarial defenses, and participating in AI threat intelligence activities. Contributes to AI governance frameworks, security tooling maintenance, and post-incident analysis for AI-related security events.
Conduct sophisticated red team testing and vulnerability assessment of generative AI models and infrastructure. Responsibilities include simulated cyber attacks on AI systems, vulnerability identification, risk analysis, mitigation strategy development, and adversarial testing of language models and agentic frameworks. Requires 5+ years penetration testing experience and proven AI vulnerabilities analysis expertise.
Design and build identity services that enable AI agents, enterprise applications, and users to interact securely. Establish authentication, authorization, and credential management for autonomous AI systems operating across enterprise environments. Design identity architectures supporting multi-agent AI platforms with secure agent provisioning, credential lifecycle management, and fine-grained access controls. Implement OAuth 2.0, OIDC, JWT, and Zero Trust principles for AI workflows. Integrate with enterprise identity providers and secure AI tool invocation frameworks. Ensure auditability and governance of AI actions in regulated federal healthcare environments.
Senior Product Security Engineer leading secure design and implementation across AlphaSense's AI-native platform. Responsibilities include architecting security controls for AI/ML systems (model training, data pipelines, inference, agentic workflows), identifying and mitigating AI-specific attack vectors (prompt injection, data poisoning, model inversion, theft), implementing model provenance and integrity controls, threat modeling, secure architecture design, and security automation. Requires 5-7+ years in product/application/cloud security engineering with deep SDLC and threat modeling expertise, hands-on code review capabilities, and working knowledge of AI/LLM security. Experience with DevSecOps, cloud security, encryption fundamentals, and authentication/authorization patterns required.
Santa Clara, CA, US; San Francisco, CA, US; San Jose, CA, US
Principal Security Researcher driving Advanced Threat Prevention detection strategy at Palo Alto Networks. Responsible for vulnerability research, exploit analysis, IPS/IDS detection development, and zero-day response. Leads detection innovation from concept to production, improves rapid response for critical vulnerabilities, and provides technical leadership to researchers. Hands-on focus on translating exploit understanding into production-quality protections, with emphasis on AI/ML-assisted detection workflows and automation to scale threat prevention capabilities.
Senior engineer in GuidePoint Security's Cloud Security Automation and AI Practice. Leads end-to-end delivery of secure AI/ML platform implementations across AWS, Azure, and Google Cloud. Designs and implements secure agentic AI solutions including multi-agent orchestration, AI gateway architectures, and policy-based controls. Architects AI governance policies for enterprise deployments. Develops AI-powered security automation solutions (compliance checks, threat detection agents, remediation workflows). Provides technical oversight, mentors junior engineers, and supports presales activities. Requires 5-7 years experience securing AI/ML workloads in cloud environments with proficiency in Amazon Bedrock, SageMaker, and Azure AI platforms.
Senior Offensive Security Researcher at SentinelOne researching evasions, building attack emulation tools, and improving detection engines for AI-native security platform. Responsibilities include proactive research of sophisticated attack techniques, tool development for detection assessments, proof-of-concept creation, and collaboration with threat intelligence and detection engineering teams. Requires 4+ years red teaming/offensive research experience, Windows internals expertise, Python/C++ coding, malware analysis, reverse engineering, EDR internals knowledge, and experience with agentic AI workflows for detection engineering tasks.
Build and operate end-to-end detection platform for Samsara's security operations. Develop MITRE ATT&CK-aligned detections across cloud, endpoint, identity, email, and application data. Own detection lifecycle from hypothesis through production deployment and retirement. Advance detection-as-code platform through version control, peer review, automated testing, and CI/CD. Evaluate AI-powered security capabilities including LLM risks, agentic frameworks, and MCP integrations. Partner with Security Operations on investigations and incident response.
Design, implement, and manage security across AllianceBernstein's AI infrastructure and products. Assess AI systems for adversarial vulnerabilities including evasion, model inversion, and membership inference attacks. Defend against AI-specific threats such as prompt injection, jailbreaking, and data poisoning. Conduct red-teaming and adversarial testing of AI models and applications before and after deployment. Secure the AI supply chain including model weights, dependencies, and deployment pipelines. Apply cloud security practices (IAM, network segmentation, secrets management) to AI infrastructure. Partner with AI and product teams to build security into development from the start. Support data privacy, governance, and alignment with AI risk frameworks. Translate findings for engineering and non-technical stakeholders.
Design and implement security controls for Generative AI systems, LLM-based applications, RAG pipelines, and agent workflows. Identify and mitigate AI-specific threats including prompt injection, data exfiltration, and model abuse. Establish guardrails for prompt handling and safe tool invocation. Secure RAG pipelines through access controls and integrity verification. Define model access controls and runtime monitoring. Conduct threat modeling and security assessments of AI systems. Build automated detection and response mechanisms for AI-specific risks. Requires 3+ years in application, cloud, or platform security engineering with hands-on distributed systems experience and strong Python/Go programming skills.
Build and operate model validation, security scanning, and content safety systems for LLMs in production. Responsibilities include developing pipelines to assess AI models for quality, correctness, and vulnerabilities; implementing model optimization and quantization techniques; building guardrail systems to enforce compliance and mitigate jailbreaking and prompt injection; and designing model evaluation frameworks that measure safety metrics. Requires 5+ years of ML experience, proficiency with PyTorch/TensorFlow, expertise in LLMs and transformer architectures, and familiarity with model safety practices and adversarial robustness.
Platform Engineer securing frontier AI evaluation infrastructure at METR, a nonprofit assessing AI capabilities and risks. Responsibilities include designing isolation and sandboxing for evaluated AI agents, implementing identity and access controls for both people and agents, vulnerability remediation across cloud infrastructure, and securing development environments. Requires 7+ years security engineering or software development experience, deep AWS/Kubernetes knowledge, and production backend/infrastructure experience. This role combines hands-on security engineering with direct responsibility for containing and monitoring AI agent execution at scale.
Senior Security Researcher at Token Security focused on AI Agent and Non-Human Identity security. Conducts deep technical analysis of AI products, LLM frameworks, and agentic tools to identify security gaps and privilege escalation risks. Designs and prototypes security enforcement models for autonomous AI Agents. Performs hands-on offensive and defensive research, develops custom research tools, and publishes technical findings at global security conferences. Collaborates with product and engineering teams to convert research into automated detections and platform features.
Lead cloud security strategy across multi-cloud environments (AWS & GCP) with focus on Zero Trust architecture and AI/LLM security. Design and enforce security boundaries for AI deployments including RAG architectures, Model Context Protocol (MCP), and Agentic AI workflows. Architect runtime security and posture management for containerized (Kubernetes/EKS/GKE) and serverless workloads. Embed automated security testing and threat modeling into CI/CD pipelines to drive Shift-Left culture. Evaluate and mitigate risks aligned with OWASP Top 10 for LLMs and MITRE ATLAS framework.
Join the AI Security Institute's Alignment Red Team to research and evaluate misalignment in frontier AI systems. Responsibilities include developing methods to automatically detect misalignment related to loss-of-control risks such as research sabotage and reward-seeking; building and running alignment evaluations; conducting pre-deployment testing with frontier AI companies; analyzing and reporting findings to governments and AI labs; contributing to public research publications; and designing software tools to improve evaluation efficiency and realism. Positions available at junior, senior, staff, and principal levels.
AI Red Teaming
Security Research
AI Security Institute (AISI), UK Government (DSIT)Government
Research Engineer or Research Scientist joining the Alignment Red Team at the AI Security Institute to detect and evaluate misalignment in frontier AI systems. Responsibilities include researching automated methods to find misalignment related to loss-of-control risks, building and running alignment evaluations, conducting pre-deployment testing of AI systems, analyzing results for frontier AI companies and governments, contributing to research publications, and designing software tooling for evaluations. The role involves threat modeling, alignment incident investigations, and mentoring external collaborators on alignment testing.
Lead technical direction for Samsara's vulnerability management and application security programs spanning cloud services, IoT firmware, and internal systems. Own mean time to remediation, build automation and tooling for vulnerability detection and response across cloud and firmware, set architectural direction, mentor engineering teams on secure practices, and participate in security incident investigations. Requires hands-on use of AI/LLM tools in security workflows including triage, detection logic, and remediation drafting.
Design, develop, and deploy autonomous AI agents integrated with enterprise security infrastructure (SIEM, EDR, XDR). Translate SOC playbooks into agentic pipelines using DAGs and multi-agent routing. Optimize production RAG workflows for security context injection and LLM performance. Implement LLM-specific security controls including prompt injection and data poisoning mitigation. Collaborate with threat analysts on human-in-the-loop escalation mechanisms and secure AI system architecture.
Design and deploy autonomous AI agents integrated with enterprise security infrastructure (SIEM, EDR, XDR) to automate SOC workflows and threat detection. Build deterministic and heuristic agentic pipelines that translate analyst workflows into production systems. Optimize RAG pipelines for real-time security context injection. Implement LLM security boundaries against prompt injection, data poisoning, and model tool-abuse (OWASP Top 10 for LLMs). Engineer human-in-the-loop handoff mechanisms for complex anomalies. Requires 2+ years AI/ML development experience and production Python/Go/Scala/Java programming.
Lead application and AI security strategy across Blink Health's infrastructure. Secure LLM integrations, AI agents, and RAG systems through design reviews and threat modeling. Develop secure patterns for prompt handling, model governance, and AI data protection. Establish secure-by-default practices via SAST/DAST automation, architecture guidance, and DevSecOps maturity. Perform threat modeling and penetration testing for critical systems. Mentor security engineers and influence engineering teams through technical leadership. Leverage AI tooling to improve security operations efficiency.
Lead technical strategy for Google Workspace account security against advanced threats. Drive vulnerability research and adversarial simulation to expose novel account takeover techniques. Design and build advanced agentic systems and simulators to autonomously detect, analyze, and mitigate account security threats. Architect customer-facing agentic tools empowering Workspace and Cloud customers to proactively secure their environments. Investigate high-severity incidents and develop long-term mitigations. Requires 5+ years security engineering experience, coding proficiency, and preferred experience building AI agents and agentic workflows for security automation.
Build autonomous security agents for enterprise use, including systems for alert triage, secure code reviews, threat modeling, and vulnerability assessment. Design agent orchestration and security controls to enable safe interaction with sensitive enterprise data. Implement novel security patterns for AI agent systems, conduct security testing, and ship production-ready agent capabilities in resource-constrained environments. Requires 5+ years of software engineering with Python expertise, AI/agent systems experience, and deep security principles knowledge.
Remote (London preferred, North America/EU/UK accepted)
Design and execute adversarial evaluations to uncover failure modes in LLM-powered web agents and chatbots. Analyze model behavior to understand and forecast security risks. Develop and prototype security-focused training and fine-tuning techniques. Augment web agents with security principles including information flow control and privilege control. Partner with engineers and researchers to translate findings into product changes and measurable security improvements. Help define security strategy and policy for building and responsibly releasing web agents.
Lead frontier LLM adversarial evaluations for offensive cyber capabilities including vulnerability discovery, exploit development, and autonomous cyber operations. Design scalable evaluation frameworks, benchmarks, and automated detection systems for AI security. Build evaluation infrastructure and taxonomies for catastrophic cyber harm assessment. Partner with frontier AI labs and ML engineers to develop guardrails and defenses. Lead a team of cybersecurity experts to establish industry standards for frontier model security.
Design and execute red-teaming frameworks and testing methodologies to evaluate foundational models, multimodal AI systems, and agents. Develop prompt injection and jailbreak research strategies across risk domains (toxicity, misinformation, copyright, child safety). Lead vulnerability analysis, oversee multi-language abuse datasets, mentor junior analysts, and document AI safety best practices. Partner with engineering and product teams to inform mitigation strategies.
Senior product security engineer at Cohere responsible for securing AI-powered enterprise products. Lead security reviews of architecture and code, threat model agentic AI capabilities, perform hands-on vulnerability testing and PoC development, and build scalable security controls and defaults. Work on emerging risks in AI systems including prompt injection, unsafe tool use, identity/delegation failures, data exposure, and tenant isolation. Partner with engineering teams to develop secure patterns and reduce recurring design vulnerabilities. Requires strong software engineering fundamentals, proficiency in Python/Go/TypeScript, experience leading security reviews for complex systems, and understanding of modern application architecture and untrusted input handling.
Principal engineer role focused on designing and building core agentic identity and security capabilities at NVIDIA. Responsibilities include architecting agent identity features for cloud and hybrid environments, prototyping secure credential brokering and token exchange mechanisms, building reusable security APIs and tools, and evaluating emerging agentic identity standards. Requires 15+ years in security/identity engineering with hands-on technical leadership, strong offensive security and red teaming background, and expertise in AI-specific security risks including prompt injection and tool misuse.
United States; San Francisco, CA; New York, NY; Washington, DC; Seattle, WA
Conduct red and purple team engagements simulating advanced threats against Anthropic's AI systems, cloud infrastructure, and deployments. Penetration test high-value AI environments, develop AI-assisted security testing tooling, and collaborate on AI-specific attack scenarios. Requires 5+ years offensive security experience, deep expertise in cloud/infrastructure security, strong engineering skills, and ability to document findings for technical and executive audiences. Role includes hands-on vulnerability discovery, adversarial testing, and security research focused on AI system resilience.
Design and build scalable ML infrastructure to support real-time safety deployments for Claude's ML-based safety classifiers and defenses. Develop monitoring and observability tools for classifier performance and data quality in safety-critical applications. Collaborate with research teams to productionize safety research into robust, scalable systems. Optimize inference latency and throughput for real-time safety evaluations. Implement automated testing, deployment, and rollback systems for ML models in production safety applications. Partner with Safeguards, Security, and Alignment teams to deliver infrastructure meeting safety and production needs.
Principal-level hands-on architect owning AI security strategy and architecture for agentic AI, LLMs, and models across product lines. Leads threat modeling for novel GenAI surfaces, sets secure-by-design standards for agentic systems, designs access-control and data-governance models for ML/RAG pipelines, and represents AI security posture externally to standards bodies and conferences. Mentors engineers on AI-specific security work. Requires 10+ years software engineering, 7+ years security engineering with AI focus, demonstrated experience with LLM/GenAI threat modeling and guardrail architecture, and fluency with OWASP LLM Top 10.
Senior security engineer role at OutSystems focused on securing AI-powered and agentic capabilities across the platform. Responsibilities include leading security initiatives across the SDLC, threat modeling for agentic systems, security assessments of applications and APIs, developing secure-by-default patterns, operating and improving security tooling, and mentoring junior engineers. The role emphasizes security by design for autonomous systems and requires hands-on experience with application security, cloud-native environments, AWS, Kubernetes, and understanding of AI-enabled systems.
Design and implement ML-driven security systems for identity risk assessment, anomalous access detection, malware classification, and sensitive data discovery. Architect high-performance inference pipelines and reasoning systems for real-time security decisions. Apply machine learning to access control, behavioral biometrics, and identity confidence scoring. Develop attack detection and threat classification models with focus on false-positive reduction. Lead technical initiatives combining ML research, systems engineering, and security expertise. Build ML platforms, feature engineering frameworks, and model management infrastructure for production security-critical environments.
Research Engineer at Anthropic focused on securing AI systems through reinforcement learning and agentic integrations. Responsibilities include designing RL environments for incident response and security analysis, developing agentic systems for autonomous investigation and remediation, and conducting security evaluations. Requires machine learning expertise combined with cybersecurity domain knowledge. Role involves both research innovation and production engineering, collaborating across security, safety, and research teams. Ideal candidates have ML research or security professional backgrounds with software engineering skills and interest in defensive cybersecurity applications.
Research Engineer role at Anthropic focused on advancing AI security through reinforcement learning. Responsibilities include developing agentic integrations for autonomous security investigation and remediation, designing RL environments for incident response and vulnerability analysis, conducting security experiments and evaluations, and delivering solutions into production training runs. Requires ML experience combined with cybersecurity domain expertise, strong software engineering skills, and ability to balance research exploration with implementation. Experience in security engineering, detection and response, or applied defensive work is preferred.
Principal Security Researcher conducting cutting-edge security research on AI-powered DevSecOps platform. Responsibilities include developing novel testing methodologies for AI agent security, conducting hands-on penetration testing, validating vulnerabilities through proof-of-concept exploits, assessing AI attack vectors (prompt injection, agent manipulation, workflow exploitation), and leading security research into GitLab's AI and agentic surfaces. Will define security requirements for AI systems, build agent-assisted vulnerability discovery tooling, and mentor team members. Requires 10+ years security research/offensive security experience, strong coding proficiency, AI framework knowledge, and deep understanding of AI attack vectors.
Staff Security Engineer on Twilio's Threat Detection and Response team. Responsible for designing and building AI Agents and Agentic workflows to conduct comprehensive threat hunting with high-fidelity detections. Develops detective tooling, performs security research, and automates incident response using SIEM and SOAR platforms. Expertise required in detecting and responding to AI-specific threats following MITRE ATLAS framework. Works across cloud infrastructure (AWS, GCP), infrastructure-as-code, and service-oriented architectures to architect scalable security solutions. Leads technical strategy, mentors team members, and partners with R&D to enhance threat mitigation and incident response capabilities.
Staff+ SRE role designing, building, and operating production infrastructure for Claude's safety systems. Owns deployment of safety classifiers and safeguards across model launches (1P, AWS Bedrock, GCP Vertex). Responsibilities include launch verification, canary rollouts, configuration drift detection, automation of safety validation pipelines, safeguards registry maintenance, and on-call incident response. Requires deep production change management experience, high-stakes release leadership, hands-on cloud platform operations (AWS/GCP), and Python proficiency.
Lead Gray Swan's biology safety capability, designing adversarial evaluations of frontier LLMs for biological misuse risks including agent acquisition, pathogen characterization, and biosecurity bypass detection. Partner with ML engineers to build scalable evaluation datasets, classifiers, guardrails, and automated red-teaming systems. Develop CBRN harm taxonomies, produce technical risk assessments for AI labs and enterprise customers, and build a team of biology subject-matter experts. Requires PhD in biology/microbiology with postdoctoral experience, deep biosecurity understanding, and experience with adversarial evaluations or AI safety research.
Fort Meade - Annapolis Junction, Maryland, United States of America
Lead technical teams at MITRE's Trustworthy & Secure AI Department performing AI adversarial threat analysis and defense research. Assess threats to AI systems, develop mitigations against adversarial tactics, and integrate secure AI solutions into government systems. Requires 8+ years AI experience, hands-on expertise in agentic AI, deep learning, generative AI, and demonstrated AI red teaming or adversarial AI experience. Provide thought leadership on AI capabilities applied to cyber challenges and mentor technical staff. Active TS/SCI clearance required.
Lead and manage a high-performing security engineering team at Cohere focused on securing AI platforms and enterprise AI systems. Responsibilities include designing and implementing vulnerability management, SAST/DAST programs, leading penetration testing of web applications and agentic AI systems, managing bug bounty programs, and embedding security practices throughout the SDLC. Requires 8+ years of application security experience with expertise in vulnerability management, cloud security, and secure development practices.
Senior Security Engineer role focused on strengthening security and resilience of AI/ML ecosystems. Responsibilities include identifying and assessing security risks in ML models and generative AI applications, designing and implementing security controls, building security frameworks for safe AI adoption at scale, integrating security into the AI development lifecycle, automating security assessments, and contributing to AI security practices evolution. Required expertise in security frameworks (OWASP), Python programming, CI/CD pipelines, security tools (SAST, DAST, SCA), and high-scalability environments. Nice-to-have skills include experience with AI frameworks (PyTorch, TensorFlow), HuggingFace, and cloud infrastructure.
Lead detection engineering capabilities in Taiwan for a SaaS security platform. Develop threat models and production detection rules for identity threats, cloud attacks, and emerging SaaS risks. Work with security research and platform engineering teams to translate attacker behaviors into accurate, scalable detections. Responsibilities include threat modeling, detection logic design, testing, telemetry definition, false positive investigation, and detection lifecycle management across cloud and SaaS environments.
Security Software Engineer supporting the operations and development of NVIDIA's AI-powered vulnerability management platform. Responsibilities include maintaining production scanning fleets powered by LLM agents, building full-stack features for the vulnerability hub, triaging and fixing issues, operating GitOps deployment pipelines, and collaborating on LLM agent harnesses that power automated security scanning across repositories and web applications. Requires Python, SQL, Linux fundamentals, and growing security expertise.
San Jose, CA; Austin, TX; Boston, MA; Dublin, Ireland (hybrid)
Develop threat models for enterprise AI systems and agent-mediated activity. Investigate how AI changes attacker operations, including speed, scale, and coordination of attacks. Recreate realistic attack scenarios in controlled environments, assess detection coverage for AI-related threats, and identify telemetry gaps. Work with Data Science and Engineering to develop behavioral detections. Contribute original research on emerging AI-attack techniques and translate findings into actionable security recommendations for detection, response, and product teams.
Individual contributor role focused on guardrails and AI red-teaming for foundation models. Responsibilities include identifying edge-case vulnerabilities, designing and training ML models and small language models in security contexts, working hands-on across model, data pipeline, and API layers, and providing reproducible findings with remediation guidance and retesting. Fully remote team across Canada.
Design and execute red-teaming campaigns against AI monitors and coding agents. Identify novel attack surfaces and vulnerabilities in monitoring systems. Build automated adversarial testing pipelines that attack monitors at scale. Conduct severity-graded failure-mode injection into real agent trajectories. Develop iterative red-team/blue-team games to escalate attack difficulty. Track research literature on agent failures and monitor evasion. Produce publications and actionable recommendations for monitor developers. Feed findings back into product hardening and internal research.
Design threat models and control protocols for coding agents at risk of misalignment or compromise. Maintain failure mode libraries, develop attack trajectories for monitor backtesting, adjudicate flagged agent behavior, and red-team Watcher's security monitors. Requires 5+ years hands-on security engineering, threat modeling expertise, code/infrastructure analysis, and ability to reason about insider-risk analogues in agentic AI systems.
Remote-Friendly, United States; San Francisco, CA; Washington, DC
Design and run evaluations measuring cyber-relevant capabilities and safeguard robustness in AI models. Execute per-release safeguard-robustness testing, analyze jailbreaks and prompt bypasses, design detection probes for cyber misuse, and build layered abuse-detection architecture. Requires hands-on cybersecurity experience including CTF participation, vulnerability research, or exploit development, combined with ML evaluation framework expertise.
Design and implement control protocols and monitoring systems for securing AI coding agents. Conduct empirical research to test monitor effectiveness across failure modes, build evaluation frameworks and datasets, fine-tune models for production monitoring, and incorporate adversarial red-teaming findings into detection systems. Requires 2+ years empirical LLM/AI research experience, strong coding agent expertise, LLM-as-a-judge experience, and Python proficiency. Work closely with research and product engineering teams on real-world agent deployments.
Security Researcher on Microsoft's AI Red Team responsible for discovering and exploiting GenAI security vulnerabilities in frontier and foundational models across Microsoft's AI portfolio (Copilot variants, Bing, GitHub, Office, Windows). Develops and scales red teaming methodologies, manages stakeholder communication, and works alongside offensive security engineers and adversarial ML experts to assess AI systems and identify safety/security risks prior to launch.
Design, build, and deploy enterprise-grade AI security platform solutions directly into customer environments. Integrate Gray Swan's threat detection and adversarial red teaming agents into complex production systems. Own end-to-end technical deployments, APIs, data pipelines, and secure system architectures. Work with customer engineering and security teams to translate AI security requirements into scalable, reliable deployments across diverse enterprise environments.
Design, deploy, and evaluate AI-powered cybersecurity solutions within virtualized environments. Fine-tune NVIDIA Nemotron models for threat detection and automated response tasks. Build CI/CD pipelines for security product validation and benchmarking. Curate datasets for security analytics. Work at the intersection of AI development and cybersecurity with offensive security researchers to advance AI-powered defense capabilities.
McLean, Virginia; Bedford, Massachusetts, United States
MITRE's Trustworthy & Secure AI Department seeks an AI Security Engineer to assess threats to AI systems, develop defenses against adversarial tactics, and integrate secure AI solutions into government systems. Responsibilities include adversarial threat analysis, vulnerability characterization in national security systems, MITRE ATLAS framework application, and capability innovation for cyber challenges. Requires Bachelor's degree plus 2 years AI experience (or advanced degree), advanced AI/ML theory knowledge, hands-on expertise in agentic AI or generative AI, Python proficiency, and ability to obtain TS/SCI clearance.
Remote (London preferred, North America/EU/UK accepted)
Researcher/research engineer focused on securing AI systems, particularly LLM-powered web agents and chatbots. Design and execute adversarial evaluations to uncover failure modes; analyze model behavior to forecast security risks; develop security-focused training and fine-tuning techniques; augment systems with information flow control and privilege control; partner with teams to implement measurable security improvements; help define forward-looking security strategy for responsible AI product development.
MITRE's Trustworthy & Secure AI Department seeks a Senior Adversarial AI Engineer to perform AI adversarial threat analysis, identify vulnerabilities in national security AI systems, and develop defenses against adversarial tactics. Responsibilities include threat assessment, vulnerability characterization, intelligence analysis and reporting, and technical subject matter expertise. Requires 5+ years AI experience with hands-on expertise in Generative AI, AI Security, Agentic AI, Testing & Evaluation, or Applied AI. Python and AI technical stack proficiency required. Active TS/SCI clearance mandatory.
Lead a team of security engineers and researchers in establishing and driving an AI offensive security research program and red team operations across AI systems, infrastructure, and emerging threats. Responsibilities include overseeing sophisticated red team operations targeting AI training pipelines, inference systems, and model architectures; developing scalable offensive security automation tools; translating security findings into strategic recommendations; and recruiting and mentoring security talent with diverse backgrounds spanning offensive security and AI/ML expertise. Requires 10+ years offensive security experience, 3+ years team leadership, and preferred deep understanding of AI/ML security threats and adversarial machine learning.
AI Security Researcher at Apollo Research. Responsible for identifying, researching, and remediating conventional and novel AI agent-related threats. Red-team internal software, infrastructure, and AI agent access controls. Design solutions for emerging AI security threats, track adversary tactics relevant to AI systems, and own findings through deployed fixes. Build detections, controls, and durable security infrastructure. Requires 5+ years hands-on security experience including offensive security, threat modeling, and red teaming. Engineering mindset essential for translating security findings into automated controls and system-level solutions.
Lead product engineering team for Watcher, a coding agent security product deployed in production monitoring billions of agent tokens monthly. Ship code in Python/TypeScript for agent security monitoring and control systems. Manage product engineers and research scientists. Coordinate delivery of security monitors, threat detection research outputs, and enterprise agent deployments. Set technical standards for secure agent architectures and incident response.
Forward Deployed Engineer owning end-to-end deployment and integration of Watcher, a production coding agent security platform. Responsibilities span deployment engineering (40%), including cloud/on-prem rollouts and agent/SIEM integrations; pre-sales and technical evaluation (30%), running POCs and security assessments with prospects; and white-glove support (30%), providing named technical contact for key customers and driving product feedback. Strong engineering foundation (3+ years production software) required, plus excellent customer communication, high agency, and comfort with enterprise security environments. Experience with coding agents, SIEM tooling, and pre-sales a plus. Salary: $222k–$290k (SF) or £149k–£195k (London).
Full-stack engineer building Watcher, a production security platform for coding agents. Responsibilities span agent-side hooks and CLI tooling, log ingestion and real-time monitoring pipelines, enterprise monitoring dashboards, and security controls (tenant isolation, encryption, access management). Own features end-to-end from requirements through production deployment. Design and operate backend systems processing high-volume agent logs with robust error handling and observability. Build integrations with enterprise security stacks and support flexible deployment models (cloud, on-prem, local). 4+ years production software experience required; full-stack capability (Python, TypeScript) essential. Strong product sense and startup-pace execution mindset.
Lead the development and implementation of Bupa's AI security architecture, standards, and governance frameworks. Define enterprise-wide AI security controls, design threat models for AI initiatives, establish risk assessment criteria, and provide strategic advisory support for secure AI adoption across the organization. Collaborate with technology, security, risk, and governance functions to balance innovation with security in a regulated healthcare environment.
Build AI-driven security scanners using frontier models to detect vulnerabilities at scale. Lead red teaming efforts against internal AI systems including jailbreak and prompt injection testing. Develop AI automation for vulnerability triage, validation, and remediation workflows across application security and incident response. Requires 3+ years offensive security experience, hands-on LLM/frontier model usage for security automation, demonstrated AI red teaming experience, and production-grade security tooling development in Python/Go.
Senior Security Engineer at Apollo Research focused on designing and deploying security controls for AI agent infrastructure. Responsibilities include building core security systems (IAM, cloud security, endpoint management, incident response), establishing security practices across the organization, evaluating security tooling, and leading major security projects. The role requires 5+ years of hands-on security experience with application/cloud/product security expertise, ability to threat-model novel AI agent risks, and engineering mindset to build custom solutions. Will work on zero-trust migrations, agentic SOC automation, sandbox hardening, and AI agent pentesting tooling.
AI Security Researcher supporting defence and national security clients. Conducts in-depth research into emerging AI security threats and vulnerabilities. Designs and develops novel tools and prototypes for system protection. Performs vulnerability analysis, reverse engineering, and security assessments. Collaborates on transitioning research into real-world capabilities and contributes to technical reports and customer deliverables. Requires active SC clearance; DV advantageous.
AI Red Teaming
LLM Security
Security Research
We Are Fr Group (Defence & National Security client)Government
Senior cloud security engineer responsible for designing and implementing autonomous AI agents for security workflows and incident response automation. Develops systems for automated vulnerability detection and remediation in enterprise cloud infrastructure. Requires hands-on expertise in AI security, adversarial testing, prompt injection defense, AI model security, and ML supply-chain security. Designs secure cloud architectures, implements security automation with IaC tools, and leads cloud security teams across AWS and Azure environments.
Staff-level security engineer responsible for foundational security posture of AI ecosystem. Design and implement secure reference architectures for Enterprise AI platforms, establish AI vetting frameworks, and develop agentic AI identity and posture management strategies. Lead enterprise security domain collaboration and mentor junior engineers. Requires 7+ years security engineering experience, 2+ years technical leadership, expertise in cloud security (AWS, GCP), container security (Kubernetes), and programming proficiency (Python, Go, Java).
Lead technical strategy for securing enterprise AI ecosystems at Twilio. Design secure reference architectures for AI platforms, establish AI vetting frameworks, and manage agentic AI identity and posture. Build preventative guardrails and mitigate risks from first and third-party AI agents. Hands-on security engineering with Python/Go and infrastructure-as-code, mentoring junior engineers and advising leadership on evolving AI security landscape.
Build and maintain AI agents and infrastructure supporting NVIDIA's security organization, including agent-enabled workflows for certifications, risk, and compliance. Design and implement MCP integrations, ETL pipelines, and data infrastructure serving security agents. Requires 8+ years automation/data engineering experience, proficiency in Python/Go/C++, production AI/agent experience, and AWS/Terraform/Airflow expertise. Background in security or cybersecurity valued.
Architect rigorous red-teaming frameworks and testing methodologies to evaluate foundational models, multimodal systems, and AI agents. Design sophisticated prompt strategies across risk domains (hate speech, misinformation, IP infringement, child safety) to expose model vulnerabilities. Conduct research into emerging jailbreak tactics, prompt injection techniques, and circumvention strategies. Serve as content and domain expert supporting risk assessment and strategy. Own engagement lifecycles from planning through delivery, mentor junior analysts, and partner with engineering and product teams to inform mitigation strategies.
Individual contributor designing and executing hands-on adversarial testing across model, application, agentic, and pipeline layers. Responsibilities include multi-turn jailbreaks, guardrail bypass, prompt injection, agent/tool misuse, dangerous-capability evaluation, and data poisoning. Deep-dive investigation of edge-case vulnerabilities, severity ranking per OWASP/NIST/MITRE/EU AI Act, and remediation validation. Requires expert Python, PyTorch/TensorFlow/HuggingFace, ML fine-tuning (LoRA/QLoRA/PEFT), adversarial attack design, and MLOps security knowledge.
Security Engineer developing AI-driven automation and intelligent solutions for vulnerability management and product security. Responsibilities include monitoring and prioritizing vulnerabilities, performing triage and risk assessment, developing Python automation for SecBOM analysis and CVE enrichment, building AI copilots for vulnerability management, and applying LLMs and RAG techniques to security knowledge management. Coordinates with development teams and PSIRT on vulnerability lifecycle management and supports security incident handling processes.
Senior-level AI red team engineer role at Carnegie Mellon University's CERT Threat Analysis Directorate. Conducts adversary emulation exercises and red teaming against real-world AI-enabled systems in national security contexts. Responsibilities include developing offensive tactics and techniques for attacking AI systems, writing exploitation tools in Python, C, BASH, and PowerShell, reverse engineering AI platform components, and assessing security across hardware, software, and network layers. Requires 8+ years offensive security experience with penetration testing, red teaming, or exploit development background, proficiency with C&C frameworks, reverse engineering tools, and TCP/IP expertise. Position involves 25% travel and requires Department of War security clearance.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University (Software Engineering Institute / CERT)AI lab
Lead AI security strategy development at Siemens DI SW, reporting to the Chief Product Solution & Security Officer. Design and deploy security measures for AI models, data, and infrastructure. Develop security frameworks for AI systems and datasets. Conduct risk assessments and threat modeling to identify vulnerabilities. Lead research into adversarial attack detection and AI security defenses. Analyze AI security incidents and conduct forensic investigations. Develop tools to monitor AI security risks and detect anomalies in model behavior. Collaborate with AI researchers, software engineers, and security teams. Ensure compliance with NIST AI Risk Management frameworks and secure AI development guidelines.
AI Red Teaming
Detection & Response
LLM Security
Siemens Digital Industries SoftwareSecurity vendor
NVIDIA seeks an AI red teamer to reduce risk and threats in networking AI products. Responsibilities include hands-on safety and security research on AI/networking systems, developing tools to expose model and infrastructure vulnerabilities, defining AI development security standards, and partnering across teams. Requires 5+ years in AI safety/security and offensive cybersecurity, expertise in LLMs/generative AI/agents/RAG, Python programming, and MLOps knowledge (Docker, Kubernetes). Strong candidates have software product design experience and familiarity with PyTorch/TensorRT.
Design, build, and deploy AI agent systems for enterprise security workflows including PQC transition, threat modeling, and automated mitigation. Architect LLM and RAG integrations with security data sources. Own full lifecycle from architecture through productization and operational deployment. Requires 5+ years experience with agentic systems, LLM production deployments, strong cryptography and secure design foundation, and Python system design expertise.
Director-level role responsible for establishing enterprise governance, security architecture, and controls for AI/ML/LLM systems across cloud, hybrid, on-premise, and OT-adjacent environments. Responsibilities include defining AI security standards and assessment methodologies, performing threat modeling, enforcing data protection and access controls, managing AI-specific incident response playbooks, integrating AI security monitoring into SOC/SIEM workflows, and overseeing vendor AI security requirements. Requires 10+ years cybersecurity/security architecture experience with hands-on expertise in securing data pipelines, APIs, cloud platforms, and ML-enabled systems. Focus on data confidentiality, model integrity, governance, and critical infrastructure safeguards.
Red team AI-enabled systems and related infrastructure to identify vulnerabilities and develop defensive countermeasures. Conduct adversary emulation exercises against real-world AI platforms used in national security contexts. Develop tactics, techniques, and procedures for attacking AI systems. Write offensive tools in Python, PowerShell, C, and BASH. Perform penetration testing and vulnerability analysis on AI platforms across hardware, software, and network layers. Reverse engineer and analyze code to identify security weaknesses. Engage in field operations and present findings to mission partners.
Red team AI-enabled systems used in national-security contexts, combining offensive cyber tradecraft with AI security expertise. Develop attack tactics, techniques, and procedures against AI systems and their supporting infrastructure. Conduct adversary emulation exercises, write exploitation tools, and prepare defenders against real-world AI threats. Requires proficiency in penetration testing, exploit development, reverse engineering, C2 frameworks, and programming in Python, C, and BASH.
AI Red Teaming
Security Research
Carnegie Mellon University (Software Engineering Institute / CERT)Government
Red team AI-enabled systems used in national security contexts, combining offensive cyber tradecraft with AI security expertise. Develop tactics, techniques, and procedures for attacking AI systems and supporting infrastructure. Write tools in Python, PowerShell, C, and BASH. Conduct adversary emulation exercises, reverse engineering, vulnerability analysis, and real-world testing of AI platforms. Requires penetration testing, exploit development, and command-and-control framework experience.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University (Software Engineering Institute / CERT)AI lab
Lead and scale multidisciplinary AI security teams focused on red teaming, adversarial testing, and AI security research. Design sophisticated attacks against LLMs, GenAI, and agentic AI systems. Research attack techniques including prompt injection, jailbreaks, tool abuse, and agent manipulation. Build and evolve automated red-teaming engines and AI security systems. Oversee advanced adversarial evaluations, define AI red-teaming frameworks aligned with OWASP, MITRE ATLAS, and NIST standards, and deploy enterprise guardrails with policy enforcement and anomaly detection.
Build trusted AI agents that augment security analyst judgment and automate detection, investigation, and response workflows. Develop context-aware agents analyzing security telemetry, design security-specific evaluations and benchmarks, optimize models and agents using production traces and analyst feedback, and take capabilities from experimentation through evaluation to production deployment. Provide technical direction for agentic AI initiatives and influence architecture decisions.
Senior Data Scientist in NVIDIA's Security and Networking Architecture group developing agentic AI systems for automated threat analysis and response workflows. Responsibilities include building and optimizing generative models with RAG and tool-augmented reasoning, fine-tuning models for production security systems, developing ML algorithms across multiple data types, creating domain-specific security datasets, and benchmarking system performance. Requires MS/PhD, 5+ years production ML/DL experience, expertise with PyTorch/TensorFlow, agentic AI frameworks, LLM fine-tuning, and inference optimization. Security and networking background preferred.
Lead and execute advanced AI red teaming engagements against large language models, RAG systems, and AI agents. Conduct multi-stage adversarial assessments including prompt injection, jailbreaking, tool abuse, model manipulation, and data exfiltration testing. Perform comprehensive penetration testing across web applications, APIs, mobile, cloud, and infrastructure. Execute secure source code reviews and red team exercises. Produce technical reports with actionable remediation recommendations and advise clients on AI and enterprise security posture.
Staff-level engineer responsible for defining technical direction and architecture for AI security products enabling organizations to adopt AI applications and agents safely at scale. Leads high-impact initiatives spanning multiple teams, turns security challenges into executable strategies, establishes standards for secure and scalable systems, and identifies architectural gaps. Requires 5+ years software engineering experience including technical leadership, deep expertise in systems and security engineering, hands-on proficiency in Go/Rust/Python, and cloud infrastructure knowledge (AWS/GCP/Azure).
Southlake, Texas; Austin, Texas; Phoenix, Arizona, United States
Engineer responsible for securing AI systems across the enterprise. Develops and maintains internal AI security libraries, builds validators for prompt inputs and output guards against insecure execution, implements PII-protection and redaction features, and writes unit tests. Integrates security libraries with developer workflows, CI/CD pipelines, and AI/ML frameworks. Requires programming in Java, .NET, or Python; understanding of secure coding principles and OWASP; familiarity with GitHub and CI/CD tools; and exposure to cloud AI/ML frameworks (AWS Bedrock, Azure OpenAI, GCP Vertex AI).
Research position at Carnegie Mellon University's CERT Division focused on AI security. Responsibilities include vulnerability discovery and assessments for AI systems, reverse engineering AI models, evaluating effectiveness of AI system defenses, and identifying emerging threats. Work involves developing analysis approaches for AI system robustness, studying the AI security ecosystem, and publishing research findings for government and industry sponsors.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University (Software Engineering Institute / CERT)AI lab
Conduct AI security research at Carnegie Mellon's CERT/SEI, focusing on vulnerability discovery, AI system robustness analysis, and defense evaluation. Reverse engineer AI systems, develop analysis methodologies and tools, study AI security ecosystems, and publish findings to influence national AI security strategy. Collaborate with cybersecurity experts, government officials, and industry practitioners on threat modeling, assessment frameworks, and emerging AI security challenges.
MLSecOps
Security Research
Carnegie Mellon University (Software Engineering Institute / CERT)AI lab
Research Engineer at Singapore AI Safety Hub building technical prototypes for AI verification mechanisms. Focus on distinguishing inference vs. training workloads on GPUs, scaling zero-knowledge proofs of AI inference, and developing privacy-preserving evaluation approaches. Work spans ML engineering, cybersecurity, cryptography, and systems engineering to create robust, auditable verification tools for international AI governance and compliance.
Conducts research into vulnerabilities and defenses of AI/ML algorithms within the Secure AI Lab. Responsibilities include counter AI research to identify threat models and weak points in AI systems, designing novel attacks and defenses, and advancing adversarial machine learning. Leads research projects, develops prototype capabilities for government customers, mentors junior researchers, and publishes original research on AI algorithm vulnerabilities and security mitigations.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University (Software Engineering Institute / CERT)AI lab
Systems engineer designing and operating data infrastructure for AI safety systems. Owns storage, pipelines, schemas, and APIs that power abuse detection, evaluation, investigation, and review workflows. Builds privacy-safe mechanisms enabling ML teams to utilize sensitive user data with purpose-tied access controls. Scales distributed ingestion and processing systems across AWS, GCP, Azure, and customer environments. Collaborates with security, privacy, and investigation teams to translate safety requirements into secure operational systems.
Design and implement AI-driven SOC automation including agentic workflows for alert triage, investigation, and incident response. Translate SOC processes into automated and agent-assisted workflows on the Torq platform. Engineer integrations across security stacks (SIEM, EDR/XDR, IdP, threat intel) via REST APIs. Design, tune, and evaluate AI agent behavior through prompt engineering, guardrails, and human-in-the-loop checkpoints. Serve as technical advisor to SOC teams and drive adoption. Requires 4-6+ years technical security experience, hands-on SOC knowledge, SIEM/EDR/XDR proficiency, Python/Bash/Go, and practical LLM/agentic AI experience.
Establish and maintain application and AI security governance across enterprise systems. Conduct threat modeling for AI use cases and workflows, assess AI-related cybersecurity and data protection risks (prompt injection, model misuse, data leakage), review AI solution architectures for security design weaknesses, embed security requirements across AI development lifecycle, manage vulnerability assessment findings (SAST, DAST, API testing), and provide expert advisory on secure AI adoption. Requires 4+ years relevant experience, threat modeling expertise, and exposure to AI/LLM technologies through implementation, governance, or security assessments.
Remote role at Mercor focused on red-teaming conversational AI models. Responsibilities include diagnosing vulnerabilities, annotating model failures, and generating actionable adversarial data to improve AI system safety. Requires hands-on adversarial testing experience and technical understanding of AI safety principles.
Capabilities researcher building Claude Security, responsible for identifying which security capabilities in frontier models are production-ready, measuring their performance on realistic cybersecurity tasks, and designing scaffolding to make them usable by non-expert security teams. Work includes rapid prototyping, rigorous evaluations, dataset and harness development for cybersecurity domains, and collaboration with engineers to operationalize capabilities. Requires 7+ years security research or engineering expertise in areas like vulnerability research, exploit development, malware analysis, or incident response, plus AI evaluation and red teaming experience.
Application Security Engineer II at Abnormal AI, securing LLM-integrated features, agentic workflows, and model supply chains on AWS. Leads threat modeling and security architecture reviews for AI-powered systems, architects secure CI/CD tooling, designs automated security testing, responds to incidents, and coaches developers on secure coding for AI-native systems. Requires 5+ years of application security with expertise in prompt injection, model supply chain, and agentic-workflow risks, strong programming skills (Python/Go/Java/TypeScript), and web application security expertise.
Individual contributor performing hands-on adversarial testing across model, application, agentic, and data pipeline layers for foundation model suites. Responsibilities include designing and executing multi-turn jailbreaks, guardrail bypass, prompt injection, agent misuse, dangerous-capability evaluation, and data poisoning attacks. Candidate will investigate edge-case vulnerabilities from red-team campaigns, reproduce findings with evidence, map severity to OWASP Top 10 for LLM Applications and NIST AI Risk Management Framework, and provide remediation guidance with retest validation. Requires expert Python, ML framework proficiency (PyTorch, TensorFlow, Hugging Face), model fine-tuning techniques (LoRA/QLoRA, PEFT), adversarial ML toolkits (ART, CleverHans, Foolbox), and threat modeling with clear communication to technical and non-technical stakeholders.
Security Researcher role at Microsoft's AI Red Team focused on discovering and exploiting GenAI security vulnerabilities in frontier and foundational models, including Bing Copilot, Security Copilot, GitHub Copilot, and Office Copilot. Responsibilities include end-to-end AI system assessment, developing scalable red-teaming methodologies, managing stakeholder communication, and collaborating with adversarial ML researchers and offensive security engineers. Requires 2+ years in security, statistics, or related field with demonstrated cybersecurity and agents testing experience; penetration testing qualifications preferred.
Lead AI security program at Blink Health's BlinkRx platform. Design multi-layer AI security framework covering data classification, detection-response, exfiltration prevention, governance, and adversarial testing. Evaluate and operate AI-specific security tooling. Architect secure MCP server deployments and agent authentication standards. Execute red-team assessments and adversarial testing of agentic workflows. Build AI security testing pipeline with automated validation. Integrate AI security controls into CI/CD pipelines. Define PHI/PII controls for all AI systems.
Design and build low-level security sensors and enforcement engines for Generative AI Security platform. Architect endpoint protection (macOS/Windows) with OS-level APIs for real-time threat detection. Own AI Security Posture Management engine design, optimize sensor performance, and mentor engineers on secure low-level systems. Partner with security researchers to translate emerging AI threats into shipped protection. Requires 6+ years systems-level programming, deep OS internals knowledge, and endpoint security framework experience.
Bellevue, Washington, US; Menlo Park, California, US; Seattle, Washington, US; Washington, District of Columbia, US; New York, New York, US
Security engineer in Meta's Applied AI organization blending hands-on security engineering with applied research. Responsibilities include building AI-powered security capabilities, prototyping AI-driven defenses, conducting adversary research, developing detection and response systems, and translating security expertise into AI-native solutions. Leverages AI tools and agents while driving their improvement through deep domain knowledge in areas such as detection engineering, threat intelligence, adversary simulation, cloud security, and AI/ML security.
Conduct state-of-the-art research on AI/ML system robustness and vulnerabilities. Develop approaches for analyzing and securing AI systems, reverse engineer malicious code, design analysis tools and methodologies, identify emerging threats to AI systems, and evaluate effectiveness of defenses. Work with government and industry stakeholders to advance AI security practices. Requires expertise in both cybersecurity (vulnerability research, disclosure, mitigation) and AI/ML (implementation, common frameworks, threat modeling).
AI Red Teaming
Security Research
Carnegie Mellon University (Software Engineering Institute / CERT)AI lab
Senior Software Engineer role at Censys building AI-powered features for SOC/threat hunting workflows. Develops and fine-tunes LLMs and RAG pipelines to reason over internet-scale data, automates threat analysis workflows, and implements secure AI guardrails. Collaborates with product and engineering teams to deploy AI-driven analytics and automation systems that help security analysts, threat hunters, and incident responders triage and investigate malicious infrastructure. Requires strong Python backend development, RAG evaluation, prompt engineering, and secure AI deployment experience in cybersecurity contexts.
Principal-level security research engineer at Elastic's Threat Research and Detection Engineering team, focusing on AI security. Responsibilities include developing detection capabilities for AI-related threats, investigating emerging attack methodologies including Generative AI Security threats, creating detection content using EQL/KQL/SQL, and leveraging AI tools to enhance threat research and detection workflows. Requires expertise in Generative AI Security, MITRE ATLAS/ATT&CK frameworks, and modern ML/LLM frameworks for production security applications.
Senior AI researcher building production-grade AI systems for vulnerability and exposure management at a cybersecurity startup. Responsibilities include designing AI-driven capabilities to analyze large-scale security data (assets, vulnerabilities, exposure context), owning the end-to-end AI lifecycle from research through production deployment, and developing LLM-based systems for security problem-solving. Requires 5+ years of applied AI/ML experience, hands-on LLM production expertise, and cybersecurity domain knowledge spanning asset management, vulnerability prioritization, and exposure analysis.
Remote (US-based; DC, NYC, SF Bay Area, Denver preferred)
Build secure, reproducible infrastructure and tooling for adversarial testing of AI systems. Responsibilities include designing cloud-based security test environments, automating attack simulations to validate controls in AI-powered systems, collaborating with red teamers to reproduce and remediate AI vulnerabilities, conducting threat modeling for AI features, and integrating security into the AI development lifecycle. Requires 5+ years security/software engineering experience, cloud infrastructure expertise (AWS/GCP, Terraform), Python proficiency, and hands-on offensive security background (penetration testing, red teaming, or adversary emulation).
Senior security engineer owning hands-on application security across product stack, including secure SDLC, CI/CD security tooling (Semgrep, CodeQL), vulnerability triage and remediation. Role includes growing responsibility for securing AI/LLM product surfaces and surfaces. Requires 3+ years hands-on security engineering experience with demonstrated build portfolio and ability to own scope autonomously.
Senior researcher role focusing on agentic AI threat research and offensive security. Responsibilities include building and deploying autonomous penetration testing agents and LLM-powered vulnerability research tools; conducting original research on emerging attack techniques using internet-wide scan data; collaborating with engineering teams to translate AI-assisted security research into product capabilities; and publishing seminal research on attacker tradecraft. Requires 5+ years hands-on penetration testing, red teaming, or adversary emulation experience, plus demonstrated expertise in agentic systems for offensive security and understanding of LLM failure modes.
Lead enterprise security strategy and architecture for AI-powered systems and Azure cloud environments. Establish security controls and runtime protections for agentic AI workflows. Conduct threat modeling for AI systems and cloud workloads, identifying risks from adversarial inputs and autonomous agents. Evaluate AI-generated code for security and define secure code review standards. Architect monitoring and hardening capabilities for AI agents at scale using Microsoft Defender and Sentinel. Embed security governance into AI/ML development pipelines and DevSecOps workflows. Research emerging AI and cloud security threats and translate insights into enterprise security improvements. Mentor teams on secure AI adoption and cloud security best practices.
Lead original technical research in AI safety at Faculty's R&D team, focusing on system understanding, interpretability, steering vectors, control & alignment, and safe deployment of language models and agentic systems. Own research projects from conception to publication, develop robust research code and engineering infrastructure, and contribute expertise to frontier lab evaluations and red-teaming efforts for misuse risk assessment. Requires strong publication track record, deep knowledge of transformer architectures, white-box analysis techniques, and Python/PyTorch proficiency.
Senior researcher at Carnegie Mellon's CERT Division focused on AI security. Responsibilities include developing approaches for analyzing robustness of AI systems, discovering vulnerabilities, reverse engineering AI models, evaluating defense effectiveness, and developing analysis tools and methodologies. Works on vulnerability assessments, threat characterization, and security research with government sponsors. Requires 10+ years experience (BS) or 8+ (MS) or 5+ (PhD) in ML/cybersecurity with practical vulnerability research, AI/ML implementation experience, familiarity with ML tools (PyTorch, TensorFlow, ART) and reverse engineering tools, and strong technical communication skills.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University (Software Engineering Institute / CERT)AI lab
Front-line AI security analyst responsible for detecting, investigating, and containing AI-related risk across AlphaSense's environment. Monitors enterprise AI usage, hunts shadow AI and rogue agent activity, analyzes AI telemetry for security findings, investigates autonomous agent threats, monitors DLP and AI data exfiltration, governs developer AI tools (GitHub Copilot, Claude Code), maintains AI logging and audit controls, tunes detection logic, and supports ISO 42001 compliance and governance reporting.
AI Security Analyst responsible for detecting, investigating, and containing risk across AI tools, agents, and models. Monitors enterprise AI usage, hunts for unauthorized and rogue agent activity, investigates autonomous agent threats, detects AI data exfiltration, governs developer AI tools, and maintains audit controls for ISO 42001 compliance. Collaborates with security operations and engineering teams to tune detection rules and support incident response.
Red Team Engineer focused on adversarial testing and safety of deployed AI systems and products. Responsibilities include comprehensive adversarial testing across product surfaces, research on novel testing approaches for agent systems and tool use, designing full kill-chain attacks that emulate threat actors, building and maintaining systematic testing methodologies, developing automated testing frameworks for continuous assessment, and collaborating with teams to translate findings into improvements. Required experience in penetration testing, model jailbreaking, LLM-specific testing frameworks, and chaining vulnerabilities in creative ways.
Remote-Friendly (Travel-Required) | San Francisco, CA | Seattle, WA | New York City, NY
Staff-level application security engineer leading M&A security due diligence and post-acquisition integration at Anthropic. Responsibilities include pre-close threat modeling and risk assessment, post-close SAST/DAST implementation, vulnerability remediation tracking, and coordinating cross-functional security integration. Role combines hands-on AppSec work (code review, threat modeling, penetration testing coordination) with AI-specific security focus, including securing agentic systems and LLM-integrated product surfaces. Develops automation tooling using LLMs to scale due diligence processes. Active participant in on-run incident response rotation and core AppSec projects.
Manager in AI Security Engineering at Deloitte responsible for securing AI/ML and GenAI solution development and deployment. Designs secure-by-design AI systems, identifies and mitigates AI-specific vulnerabilities including prompt injection and model manipulation, integrates security across SSDLC and MLOps pipelines, manages AI defensive technologies, and mentors engineering teams. Requires 6+ years in software engineering and cybersecurity with hands-on AI/ML delivery experience.
Security engineering role focused on securing frontier AI evaluation infrastructure, including agent isolation, sandboxing, cloud platform hardening, identity and access management, and securing agentic systems. Responsibilities include designing and building isolation boundaries for untrusted AI-generated code, vulnerability remediation across AWS and Kubernetes environments, implementing least-privilege access controls for both people and agents, and code review. Requires 7+ years security engineering experience, deep AWS/Kubernetes knowledge, and strong systems/network/cloud security fundamentals.
Mountain View, CA, USA; New York, NY, USA; Zürich, Switzerland
Senior security engineer leading adversarial engagements against production AI agents at Google DeepMind. Conducts multi-turn attacks targeting agentic vulnerabilities including prompt injection, tool-use escalation, and lateral movement. Develops automated red teaming frameworks and defensive guardrails. Partners directly with product teams during design phases to identify architectural flaws and translate findings into actionable engineering fixes. Requires 5+ years in red teaming, offensive security, or adversarial ML with expertise in LLM architectures and agentic workflows.
Senior Security Analyst conducting hands-on security research on AI Agents and Non-Human Identity (NHI) systems in cloud and SaaS environments. Responsibilities include deep-dive vulnerability analysis of customer infrastructure using platform tools and manual techniques, identifying security gaps in AI agent permissions and machine identities, and delivering actionable remediation reports. Role bridges technical security research with product and sales impact, staying current on emerging AI agent and cloud security threats.
Lead a security research and engineering team at an AI-native cybersecurity company building agentic systems for detection, response, threat hunting, and alert investigation. Stay hands-on with detection engineering, threat intelligence, and incident response while designing AI agents that encode expert human security practices. Manage elite security engineers, set technical direction, build evaluation frameworks for agent outputs, and shape product roadmap for autonomous defense systems.
Senior AI Security Engineer at Isomorphic Labs focusing on securing frontier AI-powered drug discovery systems. Responsibilities include adversarial threat modeling tailored to AI/ML vulnerabilities, establishing protection frameworks for ML model artifacts, designing guardrails and sandboxing for LLM ecosystems and autonomous agentic workflows, collaborating on ML lifecycle security controls from training through inference, leading AI security incident response with machine learning-driven threat hunting, and automating compliance monitoring against emerging AI regulations. Requires deep understanding of ML frameworks, cloud infrastructure security, adversarial ML threat vectors, agentic framework security, production-grade security tooling development, and pragmatic risk assessment balancing rigorous security with research velocity.
Security-focused software engineer designing and building security tools and frameworks, with emphasis on AI/ML security research and tooling. Responsibilities include developing secure software across the stack, contributing to open-source security projects, performing security code review, analyzing complex security challenges, and communicating technical concepts through publications and presentations. Works in small remote teams on projects ranging from AI/ML security frameworks to compiler-based tools.
Build LLM and agent-based systems to triage, validate, and automate security findings from bug bounties and external reports. Develop automation to assess vulnerability validity, severity, and reproducibility at scale; trace findings to root cause; and propose or generate fixes for well-understood vulnerability classes. Own bug bounty program scope and policy, and extend tooling into security testing capabilities for customers. Requires 5+ years software/security engineering, production Node.js/TypeScript, LLM/agent tooling experience, and demonstrated vulnerability assessment and triage expertise.
Design and build realistic cybersecurity environments (energy grids, telecom networks, cloud) to evaluate frontier models' defensive and offensive cyber capabilities. Study emergent AI behavior in rogue scenarios and assess loss-of-control risks. Own end-to-end problems combining AI engineering with offensive/defensive security research to help mitigate risks from increasingly capable AI systems.
Develop machine learning-based prototypes, tools, and systems for AI security applications at Carnegie Mellon University's CERT Division. Collaborate with researchers to design and execute experimental AI security solutions, including AI red teaming and adversarial ML initiatives. Support processing and analysis of large cybersecurity datasets, apply software engineering best practices to build scalable systems, and translate security research concepts into practical operational capabilities. Work alongside elite AI and cybersecurity professionals on national security-relevant AI security challenges.
AI Red Teaming
MLSecOps
Security Research
Carnegie Mellon University (Software Engineering Institute / CERT)AI lab
Research engineer at a frontier AI security lab focused on building defenses and evaluation systems for advanced AI models. Responsibilities include developing evaluation pipelines and testing frameworks, implementing agent frameworks, designing security challenges to assess model evasion capabilities, building controlled environment frameworks, and conducting AI security research with publication and customer delivery components.
Design and implement safeguards for internal AI usage, focusing on agentic systems, developer protection, and runtime security. Architect guardrails for tool-using AI systems including tool access controls, context isolation, and step-level validation. Build enforcement mechanisms governing AI behavior at runtime through interceptors, proxies, and policy engines. Design identity and access controls for non-human agents with short-lived credentials and scoped permissions. Implement logging and detection capabilities for AI activity using behavioral baselining and anomaly detection. Perform agentic system threat modeling using MAESTRO to identify and mitigate attack paths. Protect developers using AI-assisted tools by preventing sensitive data exposure and validating AI-generated outputs. Requires 7+ years security engineering experience, proven security control design and deployment, strong programming skills, and practical familiarity with agentic AI systems and OWASP guidance.
Senior ML researcher specializing in AI/ML algorithm vulnerabilities and defenses. Leads research in counter-AI threat modeling, adversarial machine learning, and defensive techniques. Develops and transitions security capabilities for government sponsors. Conducts original research in algorithm vulnerabilities, identifies attack vectors, designs novel mitigations, and evaluates defensive effectiveness. Mentors team members and collaborates on strategy for AI security research agenda.
Staff-level role designing and building autonomous AI agents and multi-agent frameworks for enterprise security operations at ServiceNow's Moveworks team. Responsibilities include architecting advanced agentic networks for proactive threat hunting, designing end-to-end incident response lifecycle automation, building MCP server orchestration systems, conducting purple team operations with internal AI red team agents, and validating automated detection and response pipelines. Acts as technical escalation point for complex incidents and strategic partner across security and infrastructure teams.
San Francisco, CA | New York City, NY | Seattle, WA
Lead Anthropic's security risk management as an engineering function. Build AI-native risk platforms using Claude to classify and triage risks. Drive end-to-end ownership of complex security problems across identity, secrets management, infrastructure, and secure frameworks. Partner with Security Engineering on threat modeling, risk quantification using methods like Monte Carlo simulation, and remediation roadmaps. Create dashboards and data pipelines for distributed risk ownership. Requires 8+ years security/software engineering experience, Python or systems language proficiency, and calibrated risk judgment.
Washington D.C., New York City, San Francisco Bay Area, Denver (US-based, remote option)
Conduct adversarial testing and red teaming of frontier AI systems to identify vulnerabilities, failure modes, and security risks. Design and execute evaluation frameworks, develop attack strategies and test cases, analyze model behavior, research emerging AI threats, and collaborate with researchers and engineers to assess AI safety and security. Contribute to real-world evaluations of advanced models and AI-enabled applications under challenging conditions.
Remote (US-based: Washington DC, NYC, San Francisco Bay Area, Denver preferred)
ML engineer designing and building evaluation systems for AI safety and model robustness. Responsibilities include designing ML experiments to evaluate capabilities and limitations of advanced AI systems, developing evaluation pipelines and benchmarks, training and fine-tuning models for safety applications, identifying model failure modes, and working on adversarial evaluations. Requires 3-5+ years ML experience, Python expertise, hands-on model evaluation, understanding of experimental design, and familiarity with agentic AI security risks.
Senior researcher developing detection methods and deploying AI agents for threat investigation workflows at scale. Responsibilities include designing detections across customer telemetry, building agentic systems for independent investigation and detection engineering pipelines, evaluating detection quality through benchmarking, analyzing diverse security telemetry (network, cloud, endpoint), and translating research into production-grade detections. Requires 5+ years in cybersecurity research, detection engineering, or incident response, with demonstrated expertise using AI coding agents and LLM workflows as core practice.
Washington DC / San Francisco / New York City / Denver (US)
Design and execute red team assessments against AI systems and applications. Develop adversarial testing methodologies, craft prompts and attack chains to uncover unsafe behavior, identify vulnerabilities and security risks, and document findings with actionable recommendations. Requires cybersecurity expertise, security tools proficiency (Splunk, Burp Suite, Nmap), Linux/terminal proficiency, Python/Bash scripting, and SIEM knowledge. Preferred experience includes AI/ML testing, prompt injection, jailbreak techniques, and offensive security certifications.
Tel Aviv-Yafo, Ra'anana, Be'er Sheva, Yokne'am Illit, Israel
NVIDIA Networking's AI red teaming role focused on improving safety and security of AI models, systems, and infrastructure. Responsibilities include hands-on safety/security research, tool development to expose AI vulnerabilities, defining secure AI development processes, and partnering with cross-functional teams. Requires 5+ years in AI safety/security and offensive cybersecurity, Python expertise, and deep understanding of LLM, MLLM, generative AI, agents, and RAG workflows.
Tel Aviv-Yafo, Ra'anana, Beer Sheva, Yokne'am Illit, Israel
Senior technical AI red teamer driving hands-on safety and security research on NVIDIA networking AI products. Develops tools and processes to expose weaknesses in AI models, systems, and infrastructure. Partners with cross-functional teams to implement AI safety and security standards. Requires 5+ years in AI safety/security, LLM expertise, and Python programming skills.
Senior security engineer role focused on securing AI-powered services. Responsibilities include designing and maintaining secure CI/CD pipelines with automated security controls, establishing secure software development lifecycle practices, conducting threat modeling and penetration testing, and assessing emerging AI-related risks including LLM applications, AI agents, prompt injection, and model supply chain security. Partner with engineering teams to evaluate and govern AI-powered development tools securely. Requires 4+ years cybersecurity/DevSecOps experience, hands-on software engineering knowledge, and practical experience with AI automation tools and agents.
Develop machine learning-based prototypes, tools, and systems for AI security applications. Collaborate with researchers on experimental AI security solutions including AI red teaming, adversarial ML, and generative AI security. Process and analyze large cybersecurity datasets (malware, NetFlow, incident data). Apply software engineering best practices to build scalable systems addressing AI security challenges. Work with elite AI and cybersecurity professionals to build technologies influencing national AI and cyber strategy.
AI Red Teaming
ML Engineering
MLSecOps
Carnegie Mellon University (Software Engineering Institute / CERT)AI lab
Develop machine learning-based prototypes, tools, and systems for AI security applications. Support AI red teaming, adversarial ML initiatives, and security analysis of AI systems including generative AI and LLMs. Process and analyze diverse cybersecurity datasets (malware, NetFlow, incident data) using ML and data analytics. Collaborate with elite AI and cybersecurity professionals to design and execute experimental AI security solutions and translate research concepts into practical operational capabilities.
Director leading LawZero's Evaluations Team to assess safety and capabilities of AI systems (Scientist AI and frontier LLMs). Responsibilities include designing evaluation strategies, building datasets and benchmarks for safety properties, overseeing red-teaming programs (automated and manual), evaluating adversarial robustness (jailbreaks, prompt injection, data poisoning), constructing evaluation infrastructure at scale, and communicating results to AI safety community. Requires 10+ years ML experience with 5+ years leading technical teams, hands-on expertise in LLM/ML safety evaluations, and track record building evaluation datasets and interactive environments for safety-relevant properties.
Senior-level role at CERT/SEI developing machine learning-based prototypes, tools, and systems for AI security applications. Responsibilities include AI red teaming, adversarial machine learning research, security analysis of AI systems, and processing cybersecurity datasets. Work spans generative AI, large language models, and counter-AI applications. Requires BS+10yr, MS+8yr, or PhD+5yr in CS, ML, cybersecurity, or related fields. Demands security clearance and software engineering expertise with containerization and microservices.
Conduct deep technical research to discover and report novel risks and attack vectors specific to modern cloud- and AI-native architectures. Identify unaddressed risk areas and translate research into product capabilities. Deliver proofs of risk and technical POCs demonstrating impact and solutions. Work with Product and Engineering teams to ensure comprehensive risk coverage. Requires 5+ years hands-on security research experience, proficiency in Python/Go and query languages, ability to drive complex multi-quarter research projects independently, and preferred expertise in enterprise AI security risks and data-driven security telemetry analysis.
Conduct applied and theoretical research into AI vulnerabilities, attack/defense methods, and security/safety benchmarking for GenAI systems. Investigate adversarial attacks, data poisoning, prompt injection, jailbreaks, and multi-modal vulnerabilities. Design and evaluate mitigation strategies including fine-tuning, guardrails, and content filtering. Develop AI security evaluation frameworks and datasets. Integrate findings into Vulcan AI security products and publish in top-tier venues.
Lead Machine Learning team developing and optimizing models for GenAI security guardrails and automated vulnerability assessment. Operationalize threat detection research into production systems, fine-tune LLMs for security intents, enhance MLOps pipelines, and ensure model reliability in production security environments. Mentor ML engineers and manage compute resources for training and inference workloads.
Lead ML team responsible for operationalizing GenAI threat detection models that power security guardrails and automated vulnerability assessment. Develop and fine-tune LLMs to detect prompt injection and multimodal threats. Establish MLOps infrastructure with rigorous model monitoring and data governance for production security environments. Bridge research findings on GenAI threats into robust, deployable models. Mentor ML engineers and manage GPU resources for both training and inference workloads in security-critical applications.
Senior AI Security Engineer responsible for red teaming and penetration testing of generative AI implementations including LLMs, agents, chatbots, and coding assistants. Combines offensive testing (prompt injection, jailbreaking, data exfiltration, agent abuse) with defensive work (guardrails, input/output controls, system prompt hardening). Designs and operationalizes security controls based on OWASP Top 10 for LLM Applications and Agentic Applications. Develops automation tools for continuous LLM testing, documents findings with remediation playbooks, and collaborates with SOC on detection. Requires 4+ years in application security/penetration testing with hands-on LLM and generative AI attack/defense experience.
Cloud security engineer responsible for designing and implementing security controls across cloud infrastructure, CI/CD pipelines, and AI-enabled environments. Responsibilities include securing AI/ML workflows, LLM applications, and model pipelines; assessing and mitigating AI-specific risks such as prompt injection and model abuse; implementing automated security testing and controls; and collaborating with engineering, platform, and AI teams to embed security throughout development and deployment. Requires 3+ years cloud security experience plus growing expertise in AI/ML and LLM security.
Research engineer role at Anthropic focused on driving safety methods for AI models, with emphasis on misuse detection and model protection. Requires AI/ML background, Python proficiency, and project management skills. Competitive compensation ($350K–$850K) with 25% minimum office presence and visa sponsorship available.
London, UK (hybrid, with UK office locations); US remote possible
Research role focused on model transparency and oversight reliability at the UK AI Security Institute. Develop detection and mitigation methods for evaluation gaming, model deception, and misalignment in frontier AI systems. Conduct red-teaming, auditing, and interpretability research on large language models. Build research infrastructure, tooling, and agent orchestration systems. Collaborate with frontier AI labs (Anthropic, OpenAI, DeepMind) and UK government on safety case reviews and alignment evaluation methodology.
New York City, NY; San Francisco, CA; Washington, DC; Remote-Friendly
Hands-on Threat Intelligence Engineer responsible for detecting and countering nation-state and criminal threats targeting frontier AI development. Tracks adversaries, builds automated pipelines and tooling to operationalize indicators into detection and alerting stacks, conducts intelligence-driven threat hunts across endpoint/cloud/identity telemetry, performs technical malware and infrastructure analysis, authors detection rules, and partners with detection engineering and incident response teams. Requires 5+ years in cyber threat intelligence or intrusion analysis, deep knowledge of threat actors and tradecraft, strong Python engineering, malware analysis expertise, and detection logic authoring experience.
Senior researcher investigating how threat actors adopt and weaponize AI across the attack lifecycle, including LLM-powered social engineering, automated vulnerability discovery, and attacks against agentic AI systems. Responsibilities include instrumenting telemetry to detect adversarial AI use, analyzing global telemetry for emerging AI threats, automating research workflows with LLMs and Python, and collaborating with threat hunters and incident responders to translate findings into detection rules and operational protections. Requires hands-on expertise in threat intelligence, malware analysis, detection engineering, and AI development.
Security Researcher at Mistral AI focused on offensive security for agentic systems. Responsibilities include proactive vulnerability hunting in AI applications and cloud infrastructure, designing red/purple team exercises, conducting penetration testing across AI-driven product suites, building offensive tooling, and partnering with defensive teams on detection engineering and incident response. Requires 7+ years offensive security experience with deep knowledge of AI/ML security risks, hands-on infrastructure assessment skills, and builder's mindset for tool automation.
Washington D.C., New York City, San Francisco Bay Area, Denver (US-based, remote eligible)
Engineering fellowship supporting high-impact AI security and safety research at 10a Labs. Responsibilities include researching and assisting with abuse detection and red teaming of AI systems, building agentic systems for automated red-teaming and experimentation, designing experiment automation, processing diverse data sources, deploying ML models, and building cloud infrastructure. Three specializations available: Software Engineering (backend systems, secure APIs, security best practices), Data Engineering (data curation, architecture design, dashboards), or Machine Learning (model training/evaluation, LLM/computer vision expertise, agent frameworks). Hands-on role at intersection of applied research and practical engineering.
London (remote-friendly with UK/EU timezone overlap required)
Member of Technical Staff in Safety for Agents team at Cohere, focused on developing safer, more secure LLMs that access external resources and take actions. Responsibilities include designing data generation and post-training algorithms, creating evaluation methods for agent safety, analyzing dataset quality and biases, hands-on LLM training on distributed infrastructure, and collaborating with ML and product teams to improve model robustness and generalizability. Requires strong software engineering, statistical expertise, and ML research background.
Research Scientist focused on agent robustness and AI safety. Responsibilities include researching AI agent capabilities with emphasis on safety and risk factors, designing harnesses to test agents' tendency to take harmful actions, creating exploits and mitigations for agent failure modes, and characterizing risks in multi-agent systems. Requires practical ML research experience, proficiency with post-training techniques (RLHF, DPO, GRPO), published research track record, and 3+ years addressing sophisticated ML problems. Red-teaming and adversarial testing experience valued.
Research Scientist role focused on AI controls and monitoring at Scale Labs. Responsibilities include designing real-time monitoring and observability methods for advanced AI models, researching layered control mechanisms including fail-safes and intervention protocols, conducting red-team simulations to identify gaps in oversight, and collaborating with policymakers and engineers on AI safety standards. Requires 3+ years ML experience, published research track record, and hands-on prototyping skills. Nice-to-haves include runtime monitoring, anomaly detection, alignment research, and post-training techniques like RLHF.
Multi-track security engineering role at Figma with AI Security specialization. Responsibilities include technical security assessments, code audits, and design reviews for AI infrastructure and products; designing solutions to secure AI models, tooling, and data pipelines; conducting penetration testing against AI systems; and building AI-powered security tooling. Also supports platform security, product security, and anti-abuse initiatives. Requires 5+ years of engineering experience and proficiency in at least one programming language.
Research-oriented engineer developing methods for AI safety evaluations at Anthropic. Designs and runs experiments to improve evaluation quality, measure model safety behavior across misuse and prompt injection scenarios, productionizes evaluation pipelines for model training and deployment, and collaborates with policy teams to translate real-world harm patterns into measurable evaluations. Requires 4+ years of software or ML engineering experience, Python proficiency, data pipeline expertise, and familiarity with LLM capabilities and failure modes.
Lead Machine Learning team developing GenAI security models for threat detection and automated vulnerability assessment. Operationalize security research findings into production LLM-based detectors for prompt injection and GenAI threats. Fine-tune language models using LoRA/PEFT for multilingual security detection. Implement MLOps pipelines with data governance, model monitoring, and drift detection. Collaborate with security research and platform teams to integrate threat detection models into Vulcan's blue team (defensive) and red team (vulnerability assessment) capabilities. Prepare multimodal detection systems for visual/audio threats. Lead ML engineers and manage compute resources.
Applied data scientist at 10a Labs focused on designing and automating adversarial red-teaming frameworks and evaluations for frontier AI systems. Responsibilities include developing evaluation frameworks, designing red-teaming strategies, leading adversarial testing initiatives (jailbreak simulation, evasion probes), automating workflows for model evaluation and AI experiments, fine-tuning LLMs for safety assessment, and coordinating with ML and infrastructure teams. Requires 3-5 years production ML experience with emphasis on model behavior analysis and safety evaluation.
San Francisco, CA | New York City, NY | Seattle, WA
Staff-level security engineer responsible for designing and building complex security systems protecting Anthropic's AI infrastructure. Focus areas include identity and secrets management for model weights and training data, developer security and supply chain hardening, infrastructure security across multi-cloud environments, and secure cryptographic frameworks. Leads threat modeling efforts, mentors security engineers, and drives security ownership across the engineering organization. Requires 8+ years of software engineering with deep security expertise, strong systems programming skills, and experience with identity systems, cryptography, Kubernetes security, and large-scale infrastructure.
Lead Machine Learning team at AIFT developing GenAI security detection models. Responsibilities include: operationalizing threat detection techniques from security research into production ML models; fine-tuning LLMs for multilingual security intents; evaluating multimodal (text, image, audio) threat detection; optimizing ML pipelines and infrastructure; implementing data versioning and monitoring for model drift; collaborating with research and platform teams on model integration; and translating technical constraints to leadership. Requires 5+ years ML engineering experience, MLOps proficiency (MLflow, Kubeflow, Airflow, DVC), Python/Docker/Kubernetes expertise, and LLM/Transformer knowledge.
Research scientist role at UK government's AI Security Institute focused on developing technical safeguards for open-weight models to prevent malicious use for CSAM and NCII generation. Responsibilities include designing threat models for AI misuse, creating scalable automated screening methodologies for platforms, developing fingerprinting and detection approaches for harmful model adaptations (LoRAs), and building technical tools and protocols for hosting platforms and OS ecosystems. Requires deep ML expertise in diffusion models, detection engineering, data pipeline development, and ability to translate technical evidence into governance guidance. Work involves collaboration with regulators, NGOs, and platforms on safety-by-design initiatives.
Lead advanced safety red-teaming efforts to identify risks, vulnerabilities, and failure modes in Generative AI models including LLMs, text-to-image, and emerging modalities. Design and execute adversarial testing, develop adversarial prompts to probe model weaknesses across multiple risk domains, analyze and communicate model vulnerabilities, and contribute to red-teaming tools and methodologies.
Subject Matter Expert on AI security within Greenhouse's product security team. Responsibilities include securing emerging AI and Machine Learning features, improving security best practices across agile SDLC, collaborating with engineers to harden AI/ML systems, staying current on AI/ML security trends, and proactively identifying and mitigating risks before deployment.
Build foundational systems for safety and oversight of AI models at Anthropic's Safeguards team. Develop infrastructure for detecting unwanted model behaviors, preventing misuse, and supporting human/agentic review. Create robust multi-layered defenses for real-time safety improvements and establish metrics and evaluation systems for AI system safeguards.
San Francisco, CA; New York City, NY; Washington, DC
Technical Cyber Threat Investigator at Anthropic. Detect and investigate misuse of AI systems for cyber operations including influence operations, malware development, and social engineering. Develop abuse signals and detection strategies to identify sophisticated threat actors. Create actionable intelligence reports on attack vectors and vulnerabilities targeting LLM systems. Conduct cross-platform threat analysis using open-source research and dark web monitoring. Utilize Python and SQL for data analysis. Build threat intelligence program with external partners and government stakeholders. Requires LLM expertise, abusive behavior detection experience, threat actor profiling skills, and threat intelligence framework knowledge.
Lead and scale multi-disciplinary AI security teams focused on red teaming, adversarial testing, and guardrail protections for GenAI and agentic AI systems. Oversee advanced adversarial evaluations, define AI red-teaming frameworks aligned with OWASP AI and NIST guidelines, operationalize automated red-team engines, and partner with product and engineering to design enterprise-ready AI guardrails with policy enforcement, monitoring, and anomaly detection. Requires 12+ years in cybersecurity/ML security and extensive leadership experience building high-performance teams.
Build and ship cybersecurity products powered by Claude AI models. Develop agent loops, tool integrations, and infrastructure for security applications. Collaborate with research teams to identify model capabilities for security use cases and iterate with customers on security solutions across the full stack from prototype to production.
AI security researcher role at a cybersecurity startup building next-generation AI-powered security products. Responsibilities include designing and implementing generative AI agents for automated threat analysis and investigation workflows, building ML-based detection models for an antivirus engine, and combining deep security research with modern AI techniques. Requires 5+ years cybersecurity research experience, proficiency in C++/Python, expertise in malware analysis and threat detection, and strong ML/data science skills. Role involves end-to-end AI system design from experimentation through production deployment.
Research Engineer developing reinforcement learning environments and training pipelines to advance Claude's capabilities in secure coding, vulnerability remediation, and defensive cybersecurity. Blend of research and engineering work involving RL environment design, experimentation, production training integration, and cross-functional collaboration with security specialists. Requires cybersecurity domain expertise paired with ML experience and strong software engineering skills.
Security researcher responsible for proactively red teaming and hacking high-impact GenAI systems at Microsoft, including Bing Copilot, Security Copilot, Github Copilot, and Windows Copilot. Conducts adversarial machine learning research to find safety and security failures in AI models and applications pre-launch. Works with interdisciplinary teams of red teamers, ML researchers, and safety experts to identify and inform mitigations for AI security and trust risks.
Evaluate and red team large language models and AI agents for safety issues and security vulnerabilities. Create repeatable, automated test cases and build scripts, tools, environments, and test harnesses for model assessment. Conduct security research on realistic attack scenarios including prompt injection and other LLM security risks. Document findings with clear reproduction steps and provide recommendations for secure coding and platform hardening.
Lead end-to-end AI red teaming security assessments for enterprise clients, focusing on LLM and agentic systems. Responsibilities include conducting comprehensive security assessments, identifying vulnerabilities (prompt injection, jailbreaking, data poisoning), developing novel testing methodologies for emerging modalities, building automation tooling to enhance delivery, and authoring detailed reports with actionable remediation guidance. Requires 3+ years cybersecurity/red teaming experience, LLM vulnerability expertise, and ability to engage with technical and executive stakeholders.
San Francisco, CA | New York City, NY | Seattle, WA; Washington, DC
Detection and Response engineer at Anthropic responsible for building security solutions to monitor threats, investigate incidents, and coordinate response efforts across the company's AI technology stack. Responsibilities include leading incident response efforts, developing novel tooling leveraging LLMs for enhanced detection and investigation, creating detections and playbooks, optimizing response workflows, and driving continuous improvement. Requires 3+ years software engineering experience plus 5+ years detection engineering, incident response, or threat hunting experience. Strong candidates have cloud environments expertise, Python proficiency, Kubernetes experience, and threat intelligence background.
Research Scientist role at UK AI Security Institute focused on AI security for chemical and biological risks. Lead technical work on capability thresholds, ecosystem engagement, and mitigation strategies for frontier AI models including LLMs. Responsibilities include evaluating frontier AI developer safeguards, collaborating on risk mitigation projects (e.g., biological/chemical classifier robustness evaluations), developing evaluation methodologies, defining risk/capability thresholds, and engaging with academic and industry stakeholders on AI safety implications. Requires background in biological/chemical science or ML, plus experience in biosecurity, AI governance, or frontier AI risk mitigation strategies.
LLM Security
Security Research
UK AI Security Institute (UK Government)Government
Security researcher focused on discovering and responsibly disclosing vulnerabilities in GenAI applications, LLMs, RAG pipelines, and multi-agent systems. Responsibilities include designing novel attacks, creating proof-of-concept exploits, authoring peer-reviewed papers for top-tier conferences (Black Hat, DEF CON, RSA), and leading public workshops on AI security techniques. Requires 4+ years of offensive security or adversarial ML experience, demonstrated jailbreaking capabilities on commercial models, strong Python skills, and proven publication track record.
One-year machine learning security research fellowship at Trail of Bits focused on evaluating state-of-the-art AI/ML systems for security vulnerabilities. Fellows conduct original research on adversarial AI scenarios including model poisoning, adversarial examples, jailbreaks, and data extraction attacks. Responsibilities include designing novel attack and defense methodologies, developing evaluation frameworks, building open-source AI/ML security tools, and collaborating with the AI Assurance team on client engagements. Positions researchers at the intersection of cutting-edge AI/ML research and real-world security with dedicated time for independent research, publication, and conference engagement.
Software engineer on Anthropic's Safeguards team building safety and oversight mechanisms for AI systems. Develops monitoring systems to detect unwanted model behaviors, builds abuse detection infrastructure, and creates multi-layered defenses for real-time safety improvement at scale. Surfaces abuse patterns to research teams for model hardening and enforces terms of service and acceptable use policies. Requires 8+ years software engineering experience and expertise in detection, adversarial inputs, and AI/ML trust and safety systems.
Remote, part-time contract role designing and executing adversarial tests against LLMs, AI agents, and RAG pipelines. Responsibilities include creating attack prompts, testing prompt injection/jailbreaks/data exfiltration, evaluating LLM attack surfaces using OWASP Top 10 for LLMs, defining scoring rubrics, and documenting reproducible security findings with risk ratings and mitigations. Uses red-team frameworks (garak, PyRIT) and requires Python, Bash, PowerShell, Docker, and cybersecurity/penetration testing background.
Design and implement security frameworks for GitLab's internal AI systems, including LLMs and AI agents. Secure Model Context Protocol implementations, manage non-human identity systems with zero-trust access controls, govern internal AI tool usage through DLP and monitoring, and prevent data leakage through AI systems. Collaborate cross-functionally on AI security adoption and evaluation of enterprise AI tools.
Design, build, and deploy AI-powered security agents for threat detection, incident analysis, and automated response. Develop agentic workflows that autonomously perform log forensics, threat hunting, and incident response tasks. Integrate agents with data lakes, SIEM platforms, and security toolstacks. Requires 5+ years professional experience with 3+ years in cybersecurity operations, hands-on incident response, Python proficiency, LLM/agentic framework experience, and cloud security knowledge.
Design and maintain detection engineering practice for AI/ML systems at the UK Government's AI Security Institute. Define threat models for frontier AI safety research, write detection rules and hunt queries for AI-specific risks including model weight exfiltration, dataset poisoning, training pipeline compromise, GPU abuse, and inference endpoint attacks. Develop AI-focused incident playbooks, extend cloud-native telemetry to cover model registries and inference gateways, and collaborate with DSIT's SOC to correlate AI safety signals with security events. Requires strong detection-as-code expertise, AWS cloud instrumentation, and practical understanding of AI/ML attack surfaces and threat frameworks.
AI Red Teaming
Detection & Response
MLSecOps
AI Security Institute (UK Government / DSIT)Government
Red team specialist conducting sophisticated security analysis and testing of generative AI models, language models, and image generation systems. Responsibilities include simulated cyber attacks on AI infrastructure, vulnerability assessment, risk analysis, and collaboration on mitigation strategies. Requires proven AI vulnerability analysis experience, 5+ years offensive cybersecurity background, Python proficiency, and agentic framework familiarity.
Join the AI Safety Institute's Safeguard Analysis Team to research and develop interventions that secure frontier AI systems from abuse. Responsibilities include assessing security threats to advanced AI systems, developing novel attacks against LLMs, conducting red-teaming evaluations, and building infrastructure for running security assessments. The role spans research-oriented work (threat analysis, attack development) and engineering-oriented work (evaluation infrastructure). Candidates should have experience in AI security, computer security, machine learning, red-teaming, and proficiency with large language models and Python. Mentorship from world-class researchers including alumni from Anthropic, DeepMind, and OpenAI.
Threat Detection Researcher at Wiz responsible for developing cloud-native threat detection capabilities. Drives the full lifecycle of security detections from research and data analysis to production deployment. Designs behavioral baselines for cloud environments, expands detection engine with novel telemetry sources, and conducts deep technical research into cloud services to uncover attack vectors. Investigates real-world attacks and hunts emerging threats targeting cloud ecosystems. Requires 6+ years hands-on security/threat research experience, Python/Go proficiency, and proven track record of delivering actionable security impact.
Join Wiz's Threat Research team to develop cloud-native threat detection capabilities. Drive the complete lifecycle of security detections from research and data analysis to production deployment. Design behavioral baselines for complex cloud environments, develop high-fidelity detections from diverse signals, and expand the detection engine with novel telemetry sources. Conduct deep technical research into cloud services to uncover attack vectors, investigate real-world attacks across cloud platforms and identity providers, and hunt emerging threats targeting the cloud ecosystem. Requires 6+ years of hands-on security/threat research experience, proficiency in Python, Go, and query languages, plus background in incident response, red teaming, or threat hunting.
Detect and respond to malicious uses and abuse of AI systems. Investigate threat actors and harmful behaviors through SQL and Python data analysis, OSINT cross-referencing, and detection pipeline development. Support incident escalations and provide investigative reports for frontier AI labs and platforms. On-call responsibilities for urgent security escalations.
Research Engineer on Alignment Science at Anthropic focused on exploratory experimental research on AI safety. Responsibilities include building and running ML experiments to understand and steer AI system behavior, testing robustness of safety techniques through adversarial model training, running multi-agent RL experiments, building tooling to evaluate LLM-generated jailbreaks, and contributing to alignment stress-testing and pre-deployment safety assessments. Work feeds into key safety efforts including the Responsible Scaling Policy and involves collaboration with Interpretability, Fine-Tuning, and Red Team colleagues.
New York City, NY; Seattle, WA; San Francisco, CA; Washington, DC
Build and scale AI-powered security analytics infrastructure at Anthropic. Architect and implement data pipelines processing security telemetry, develop ML-powered detection systems, and create solutions leveraging Claude for security operations. Design scalable infrastructure for detection development through incident response, prototype new security tooling, and mentor engineers on the Security team.
Remote-friendly (San Francisco, Seattle, New York)
Lead application security for Claude and related AI systems at Anthropic. Design and operate LLM-driven security systems including automated code analysis, vulnerability remediation, and threat modeling. Secure novel AI infrastructure including multi-agent orchestration, sandboxed code execution, and delegated credentials. Own security systems end-to-end, conduct threat modeling for agentic systems, operate bug bounty programs with AI-assisted triage, and respond to incidents in production AI systems. Use Claude as a primary security tool while providing human judgment and system-level reasoning.
Red team engineer focused on identifying vulnerabilities in generative AI systems through adversarial testing. Responsibilities include designing red teaming assessments for LLMs, conducting threat emulation (prompt injection, data poisoning, model drift), ethical bias audits, producing detailed vulnerability reports, and developing a training program for red teaming best practices. Collaborates with ML engineers and researchers to evaluate model robustness under adversarial conditions and provide defensive recommendations.
Conduct in-depth research on AI-specific security threats including adversarial attacks, model tampering, and data privacy issues. Develop and implement strategies to detect and mitigate AI security vulnerabilities in NLP, computer vision, and other ML domains. Collaborate with cross-functional teams to integrate AI security measures into products and stay current with AI security research trends. Requires 5+ years AI/ML experience with demonstrated security research publications and hands-on experience deploying secure AI systems.
ByteDance seeks an AI Security Researcher to conduct research and analysis of security threats to AI technology. Responsibilities include identifying vulnerabilities in AI systems, developing countermeasures, conducting penetration testing and risk assessments, monitoring system security, developing security protocols, analyzing potential security incidents, and collaborating with cross-functional teams to implement security measures. The role requires expertise in AI security with focus on safeguarding cutting-edge AI systems and staying current with industry threats and compliance standards.
Security engineer specializing in red teaming and penetration testing for Cymetrics, a cybersecurity SaaS platform provider. Responsibilities include planning and executing red team exercises, conducting penetration tests across modern web frameworks (React, Angular, Vue.js), performing lateral movement and network reconnaissance, researching vulnerabilities in websites and open-source projects, assisting with automated security tool development, and collaborating on proprietary security product improvements. Requires 3+ years red teaming experience, expertise in OWASP methodologies, web vulnerability assessment, and client communication. The role supports a comprehensive security assessment SaaS platform that includes AI model vulnerability verification.