Jobs for AI Security Engineers

Build autonomous AI security agents that automate security operations including alert triage, secure code review, threat modeling, and vulnerability assessment. Design agent orchestration systems and security controls to enable safe interaction with enterprise data. Implement security infrastructure for high-trust environments, conduct security testing of agents and platforms, and research novel security patterns for agent systems.

• AI Red Teaming
• LLM Security
• MLSecOps

Amazon is hiring a Security Engineer for their AI Security team to design and validate security controls for AI/ML services including Amazon Bedrock, SageMaker, and generative AI platforms. The role involves analyzing security of AI/ML applications, discovering and addressing security issues, building security automation, threat modeling, penetration testing, and developing new testing methods. Responsibilities include secure SDLC practices, security reviews, tool development, and mentoring. Requires 2+ years in security vulnerabilities identification, scripting/programming, and system troubleshooting. This is a hands-on security engineering position focused on protecting enterprise-scale AI/ML services.

• LLM Security
• MLSecOps
• Security Research

MITRE's Trustworthy & Secure AI Department seeks a Senior Adversarial AI Engineer to perform AI adversarial threat analysis and develop defenses against adversarial AI tactics. Responsibilities include assessing threats to AI-enabled systems, identifying and characterizing vulnerabilities in real-world national security systems, and conducting research on AI security mitigations. Requires 5+ years of AI experience with hands-on skills in generative AI, AI security, agentic AI, testing, or applied AI; Python proficiency; ability to communicate technical concepts; and active TS/SCI clearance. Preferred experience in AI red teaming, threat analysis, and intelligence reporting. Senior-level position requiring on-site presence.

• AI Red Teaming
• Detection & Response
• Security Research

MITRE's Trustworthy & Secure AI Department seeks an AI Security Engineer to assess threats to AI systems, research and develop defenses against adversarial AI tactics, and integrate secure AI solutions into government systems. Responsibilities include performing adversarial threat analysis on real-world national security systems, utilizing the MITRE ATLAS framework, contributing to AI capabilities for cyber operations, and communicating findings to stakeholders. Requires Bachelor's degree plus 2+ years AI experience (or equivalent); advanced understanding of AI/ML theory; hands-on experience with agentic AI, reinforcement learning, computer vision, or generative AI; strong Python skills. Preferred: advanced degree, deployment experience, AI red teaming, adversarial AI, or AI security governance background.

• AI Red Teaming
• MLSecOps
• Security Research

Lead Anthropic's coordinated vulnerability disclosure program and CVE Numbering Authority (CNA), managing model-level security vulnerabilities and jailbreak disclosures. Own the public disclosure program end-to-end, coordinate multi-party disclosures with researchers and vendors, triage vulnerability submissions, and represent Anthropic in the security research community. Build and scale the disclosure function, establish partnerships with threat-intelligence organizations, and ensure vulnerability findings inform model-release decisions. Requires experience operating coordinated disclosure programs, managing vulnerability queues, handling embargoed information, and ideally CNA or PSIRT experience.

• AI Red Teaming
• Detection & Response
• Security Research

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

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

Lead engineer for NVIDIA's Agent Policy Fabric core platform, responsible for building runtime policy verification, signed policy bundle handling, trust-root management, policy projection, conformance testing, and cross-runtime integration for governed agentic systems. Design and harden authorization APIs, cryptographic verification pipelines, and fail-closed security defaults. Collaborate with runtime teams on public interfaces for policy enforcement, runtime attestation, and audit. Define versioning, latency budgets, and architecture specifications for product security and enterprise partner adoption.

• Governance & Compliance
• LLM Security
• Security Research

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.

• AI Red Teaming
• LLM Security
• Security Research

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.

• AI Red Teaming
• LLM Security
• MLSecOps

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

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

Develop and answer open-ended AI security research questions to understand, measure, and reduce risk in frontier models, agentic systems, and AI platforms. Build practical methods, prototypes, and evaluations revealing how AI systems fail under adversarial conditions. Explore LLM and agent security, adversarial testing, model evaluation, vulnerability discovery, and autonomous response. Translate research into proof-of-concept demonstrations, benchmarks, and secure-by-design recommendations for engineering teams. Requires 12+ years in AI security, cybersecurity research, or offensive security with demonstrated original research impact and hands-on Python/ML systems development.

• AI Red Teaming
• LLM Security
• Security Research

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.

• AI Red Teaming
• Detection & Response
• LLM Security

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.

• Detection & Response
• LLM Security
• ML Engineering

Senior technical architect designing, building, and deploying secure agentic AI systems on accelerated computing platforms. Responsibilities include architecting multi-agent workflows with guardrails and policy enforcement, integrating AI models into security detection and response products, implementing threat triage and remediation agents, designing confidential AI deployments with GPU attestation and KMS integration, and addressing adversarial risks such as prompt injection and jailbreaks. Requires 8+ years in engineering/ML/enterprise software, hands-on production experience with LLMs and agentic AI, depth in AI/LLM security or confidential computing, and familiarity with safety frameworks and red-teaming practices.

• AI Red Teaming
• Detection & Response
• LLM Security

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

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

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

Software engineer building data platforms and pipelines that power AI safety and oversight mechanisms. Responsibilities include designing data foundations for misuse detection and prevention systems, implementing governance and access controls for sensitive data, and operating infrastructure across multiple cloud providers. Focuses on correctness, retention discipline, and portability to support Anthropic's Safeguards team in monitoring models and preventing misuse.

• Detection & Response
• MLSecOps

Lead end-to-end AI red teaming security assessments for enterprise clients. Conduct comprehensive security testing of LLM applications and agentic systems, including prompt injection, data poisoning, and jailbreaking. Develop novel red teaming methodologies for emerging modalities and automate testing workflows. Author security assessment reports with actionable findings for technical and executive stakeholders. Collaborate with research teams to translate academic findings into practical testing approaches.

• AI Red Teaming
• LLM Security
• Security Research

Senior security engineer conducting offensive red team operations against AI systems at Amazon. Responsibilities include executing sophisticated red team operations across AI portfolio (training pipelines, inference systems, model architectures), performing offensive security research on AI threats and supply chain security, discovering and exploiting vulnerabilities in AI infrastructure and applications, developing automated tools for threat emulation and scaling offensive capabilities, and translating technical findings into actionable security recommendations. Requires 5+ years offensive security experience; preferred qualifications include AI/ML security knowledge, adversarial ML, red team operations, and cloud platform expertise.

• AI Red Teaming
• MLSecOps
• Security Research

Build and maintain the harness and platform infrastructure for NVIDIA's AI Safety & Security Engineering team that develops AI-powered tooling to find, validate, and patch software vulnerabilities. Design agent harness systems, evaluation infrastructure for running security research experiments, and reproducibility tooling. Partner with security researchers and evaluation engineers to support AI-driven vulnerability detection and validation workflows. Requires 5+ years software engineering experience, strong Python skills, and familiarity with agent frameworks, LLM orchestration, or ML infrastructure.

• AI Red Teaming
• MLSecOps
• Security Research

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.

• AI Red Teaming
• LLM Security
• Security Research

Own production change management and operational deployment for Claude's safety systems. Stand up, configure, and verify AI safety classifiers across all deployment platforms (1P, AWS Bedrock, GCP Vertex). Deploy new safety classifiers, run canary rollouts, detect configuration drift, and lead incident response. Automate launch runbooks into repeatable pipelines and build safeguards registry with full provenance tracking. Requires 8+ years SRE/software engineering experience, hands-on cloud deployment expertise, and production incident response track record.

• Detection & Response
• MLSecOps

Senior Security Engineer - AI responsible for designing and embedding security controls across AI-driven and agentic systems. Conducts AI-specific threat modeling, embeds security across agentic SDLC phases, develops reusable security patterns, validates infosec solutions through POCs and pilots, and works on automating security processes at scale. Requires 7+ years information security experience with hands-on application/infrastructure background, practical exposure to AI and agentic architecture (MCP, RAG, agents, tools), and ability to translate security requirements into engineering solutions.

• AI Red Teaming
• LLM Security
• MLSecOps

Lead technical direction and execution of AI attack simulation product at HiddenLayer. Design agentic workflows, tool integrations, and evaluation frameworks that translate adversarial AI techniques into safe, repeatable security testing. Establish AI-first development workflows, mentor engineering teams, and partner with Product and Security Research to shape strategy and roadmap. Requires 10+ years software engineering with distributed systems expertise, production AI/agentic systems experience, and cybersecurity background in attack simulation, red teaming, or AI security.

• AI Red Teaming
• MLSecOps
• Security Research

Lead AI security program for healthcare tech platform. Design multi-layer AI security framework spanning data classification, detection, governance, and adversarial testing. Execute red-team assessments against AI applications and agentic workflows. Architect secure MCP server deployments and agent authentication standards. Perform adversarial testing for privilege escalation and tool misuse. Integrate AI security controls into CI/CD pipelines. Develop automated testing for AI systems and pipelines. Requires 7+ years security engineering, hands-on adversarial AI techniques, NIST AI RMF/ISO 42001 knowledge, and Python/GitHub skills.

• AI Red Teaming
• LLM Security
• MLSecOps

Researcher at Carnegie Mellon University's CERT Division focused on AI security. Conducts vulnerability discovery, reverse engineering of AI systems and models, evaluates robustness of AI defenses, develops threat analysis methodologies, and influences national AI security strategy. Requires BS with 8 years, MS with 5 years, or PhD with 2 years experience in ML, cybersecurity, or related fields, plus practical experience in vulnerability research, reverse engineering, and AI/ML implementation.

• Detection & Response
• ML Engineering
• Security Research

Develop validation and patch methods for AI-powered vulnerability detection and remediation systems. Establish standards for confirming vulnerabilities are real and reachable, and for generating safe, correct fixes. Work with AI-assisted analysis workflows to identify and fix software vulnerabilities in NVIDIA-internal targets, applying rigorous security judgment to define trustworthy patching approaches. Requires 12+ years in security research or software engineering with hands-on expertise in vulnerability research, fuzzing, program analysis, and secure coding in C/C++/Python.

• MLSecOps
• Security Research

Build secure, reproducible infrastructure and tooling for AI security evaluations at 10a Labs. Design cloud-based environments, automation, and tooling supporting scalable adversarial testing of AI systems. Develop and automate attack simulations to validate security controls and improve resilience of AI-powered systems. Conduct threat modeling and security design reviews. Collaborate with red teamers to reproduce and remediate vulnerabilities uncovered during AI security assessments. Requires 3–5 years security/software engineering experience, hands-on offensive security work, Python, AWS/GCP, infrastructure-as-code, and familiarity with LLMs and AI security.

• AI Red Teaming
• MLSecOps
• Security Research

Secure AI system integrations, LLM deployments, and RAG pipelines across corporate environment. Identify and mitigate AI-specific threats including prompt injection, model poisoning, and adversarial attacks. Design and maintain DLP policies for AI channels. Conduct threat modelling and security assessments for AI tools and vendor integrations. Develop guardrails and monitoring for anomalous AI behaviour. Author AI security policies and maintain risk registers aligned with EU AI Act, NIST AI RMF, and ISO/IEC 42001 in regulated financial services context.

• Governance & Compliance
• LLM Security
• MLSecOps

Founding technical leader for NVIDIA's AI Safety & Security Engineering team. Responsible for architecting AI-powered vulnerability discovery and patching systems, defining canonical harness architecture and engineering standards for safety-critical AI systems, guiding technical roadmap for Find-Validate-Patch pipeline, and mentoring founding engineers. Bridges exploratory research and production-grade engineering for secure AI systems.

• AI Red Teaming
• MLSecOps
• Security Research

Design and build benchmarking and evaluation infrastructure for AI-powered security tooling at NVIDIA's AI Safety & Security Engineering team. Responsibilities include creating metrics and protocols to measure AI system effectiveness in vulnerability detection, designing reproducible experiments, mapping results to code and runs, and automating measurement infrastructure. Work directly with security researchers to evaluate agent and LLM behavior in security contexts.

• MLSecOps
• Security Research

Lead and build the foundational AI Safety & Security Engineering team at NVIDIA. Own delivery of vulnerability finding, validation, and patching systems powered by AI. Hire and mentor engineers across security research, harness engineering, and platform engineering disciplines. Drive technical roadmap execution, architect trade-offs in ML-based security tooling, and communicate engineering progress across the organization. Requires 12+ years software engineering experience with 5+ years managing complex systems teams.

• Detection & Response
• ML Engineering
• Security Research

AI Security Researcher at Carnegie Mellon University's Software Engineering Institute (CERT Division). Develops approaches for analyzing robustness and vulnerabilities in AI systems. Responsibilities include reverse engineering AI models and malicious code, vulnerability discovery and assessment, designing analysis tools and methodologies, evaluating effectiveness of AI security defenses, and conducting research on AI security threats and mitigations. Requires BS with 8 years, MS with 5 years, or PhD with 2 years in ML, cybersecurity, or related discipline. Requires practical vulnerability research experience, familiarity with AI/ML frameworks (PyTorch, TensorFlow, NumPy), reverse engineering tools, and programming proficiency.

• AI Red Teaming
• MLSecOps
• Security Research

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

Lead Anthropic's cybersecurity research program focused on AI-driven offensive and defensive capabilities. Oversee research on how frontier AI models impact cybersecurity, design and execute AGI-scale security research, hire world-class researchers, build autonomous AI systems for vulnerability discovery and patching, run purple-team simulations with AI attackers and defenders, and develop defenses to secure the world in the era of advanced AI. Work cross-functionally with Training, Safeguards, and Product teams to integrate findings into model development and deployment. Translate technical research into policy demonstrations.

• AI Red Teaming
• Detection & Response
• Security Research

Lead security frameworks and libraries for AI model development at Anthropic. Design and own cryptographic frameworks, secure serialization, and authorization systems that enable secure handling of model weights, training data, and customer data. Manage and grow a security engineering team, partner across product and infrastructure teams, conduct threat modeling and risk assessment, and drive framework adoption across the organization. Requires 3+ years managing security teams and 5+ years hands-on security engineering experience with deep expertise in securing complex architectures.

• Governance & Compliance
• MLSecOps
• Security Research

Staff+ engineer on Anthropic's Safeguards Review Tooling team building investigation, review, and enforcement systems for Claude models and products. Responsibilities include developing case management and decision-logging tooling, creating platform layers for review workflows, scaling review through Claude-assisted automation, and implementing privacy-preserving and audit mechanisms. Works cross-functionally with policy, operations, and data science to reduce handling time and decision error in harm detection and enforcement workflows.

• Detection & Response
• Governance & Compliance
• LLM Security

Lead the Interventions team at Anthropic's Safeguards organization. Own the composable arsenal of safety intervention systems deployed across Anthropic's products, API, and third-party clouds. Manage engineers shipping production ML safety-enforcement systems; drive cross-functional work with ML infrastructure, research, product, and policy teams. Own production reliability, incident response, SLOs, and verification processes for safety systems. Set measurement-backed standards for intervention quality and represent safety-product tradeoffs to leadership.

• Detection & Response
• Governance & Compliance
• LLM Security

Red Team Engineer at Anthropic's Safeguards team conducting comprehensive adversarial testing of AI systems and products. Responsibilities include designing creative attack scenarios combining multiple exploitation techniques, researching novel testing approaches for agent systems and tool use, executing full kill-chain attacks simulating real-world threat actors, developing automated testing frameworks for continuous assessment, and translating security findings into product improvements. Requires penetration testing, red teaming, application security, model jailbreaking expertise, and hands-on experience with security testing tools and LLM-specific testing frameworks.

• AI Red Teaming
• LLM Security
• Security Research

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.

• AI Red Teaming
• Application Security
• LLM Security

Security operations and incident response engineer specializing in AI/ML systems. Develops and executes incident response playbooks for AI-specific threats (prompt injection, model poisoning, data exfiltration, adversarial attacks). Monitors and secures generative AI systems, LLMs, and AI-powered applications. Conducts AI threat modeling, vulnerability assessments, and post-incident analysis for AI-related security events. Reviews model security properties and robustness. Contributes to AI governance frameworks and policies. Requires 5+ years information security operations, 3+ years incident response, and 2+ years AI/ML security experience.

• Detection & Response
• LLM Security
• MLSecOps

Applied Security Researcher investigating AI, cloud, and code technologies to unlock new security features at Wiz. Conduct threat modeling and attack vector research for AI-native architectures. Design and implement agentic workflows for contextual understanding of cloud and application environments. Build functional prototypes and PoCs. Requires 5+ years security research experience, cloud security background preferred, with specialized AI security focus and model evaluation knowledge.

• AI Red Teaming
• LLM Security
• Security Research

GenAI Security Engineer conducting security architecture reviews, threat modeling, and risk mitigation for GenAI and agentic AI platforms. Responsibilities include identifying threats like prompt injection, jailbreak, data leakage, and model poisoning; reviewing architectures for Vertex AI, AgentSpace, and Copilot Studio; validating security requirements against OWASP LLM Top 10 and MITRE ATLAS; and reviewing IAM, secrets management, API security, and cloud controls. Requires 7+ years cybersecurity experience, hands-on threat modeling, cloud security expertise (Azure/GCP/AWS), and experience securing LLMs, RAG pipelines, and agentic systems.

• Application Security
• LLM Security
• Security Research

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

Design and build evaluation methods and infrastructure for AI safety at Anthropic. Responsibilities include developing methodologies to measure model behavior across misuse and prompt injection scenarios, constructing high-quality datasets representing real-world harm patterns, building evaluation harnesses for agentic investigation systems, and productionizing safety evaluations into model training and deployment pipelines. Work spans applied ML research, dataset engineering, and detection/response infrastructure for Claude model safety and abuse prevention.

• AI Red Teaming
• Detection & Response
• LLM Security

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 runtime enforcement mechanisms (interceptors, proxies, middleware) governing AI behavior at execution time. Design identity and access controls for non-human agents with short-lived credentials and scoped permissions. Implement logging and detection for AI activity including behavioral baselining and anomaly detection. Perform threat modeling using MAESTRO to identify attack paths and translate findings into practical safeguards. Protect developers using AI tools by preventing sensitive data exposure and validating AI-generated code.

• Detection & Response
• LLM Security
• MLSecOps

Lead Anthropic's Security Risk function, responsible for identifying, prioritizing, and treating complex security risks through AI-native platforms and automation. Design and build risk tooling powered by Claude for classification, triage, and continuous risk landscape sensing. Conduct threat modeling and risk quantification across identity, secrets, infrastructure, and supply chain security. Partner with Security Engineering to drive remediation roadmaps and build risk engineering culture. Mentor engineers across the organization on risk assessment and ownership. Requires 8+ years of security/software engineering experience with demonstrated ability to own complex security problems end-to-end.

• Detection & Response
• LLM Security
• MLSecOps

Red Teaming Fellow conducting adversarial testing of frontier AI systems and models. Responsibilities include designing and executing red teaming exercises to identify vulnerabilities and failure modes, developing attack strategies and test cases, analyzing model behavior under challenging conditions, documenting findings, supporting evaluation framework development, and researching emerging AI threats and attack techniques.

• AI Red Teaming
• Security Research

ML engineer designing and building evaluation systems for AI safety and model robustness. Responsibilities include designing experiments to evaluate capabilities and failure modes of advanced AI systems, developing evaluation pipelines and benchmarks, training and fine-tuning models, analyzing security risks to AI agents, and building infrastructure for large-scale evaluations. Supports frontier AI organizations with adversarial red teaming and model evaluation.

• AI Red Teaming
• ML Engineering
• Security Research

Design and execute red team assessments against AI systems and applications. Develop adversarial testing methodologies to evaluate system security and robustness. Craft prompts, attack chains, and adversarial inputs to uncover unsafe behavior. Identify vulnerabilities and failure modes through offensive testing. Analyze system outputs to assess security and safety risks. Collaborate with engineers and researchers to improve system security. Requires 2–5 years of cybersecurity experience, proficiency with security tools (Splunk, Burp Suite, Metasploit, etc.), scripting capability, and familiarity with AI/ML attack vectors including prompt injection and jailbreak techniques.

• AI Red Teaming
• Application Security
• LLM Security

Expression of interest for red team positions at the UK AI Security Institute. Roles involve cutting-edge research to identify, evaluate, and stress-test vulnerabilities in frontier AI systems. Work spans three areas: Alignment (detecting misalignment and loss-of-control risks), Misuse (stress-testing safeguards and developing attack tooling), and Control (evaluating control measures using adversarial ML techniques). Findings inform AI companies (Anthropic, OpenAI, DeepMind) and UK/allied governments on deployment and policy.

• AI Red Teaming
• Security Research

Deploy, integrate, and troubleshoot Vulcan—a GenAI cybersecurity platform providing automated red and blue team services—into enterprise on-premise, VPC, and hybrid cloud environments. Architect data pipelines and automation for AI models and agent frameworks (e.g., Harness). Optimize containerized and Kubernetes deployments with focus on GPU scheduling and network-isolated environments. Serve as technical bridge between enterprise clients and engineering teams on AI vulnerability defense, compliance concerns, and security policy translation. Provide technical training and translate real-world edge cases and performance bottlenecks into product improvements.

• AI Red Teaming
• LLM Security
• MLSecOps

Develop machine learning-based prototypes, tools, and systems for AI security applications. Collaborate with researchers on experimental AI security solutions, including AI red teaming and adversarial ML initiatives. Apply software engineering best practices to build scalable systems, process large cybersecurity datasets (malware, NetFlow, incident data), and translate research concepts into operational capabilities. Work with elite AI and cybersecurity professionals on technologies influencing national AI security strategy.

• AI Red Teaming
• MLSecOps
• Security Research

Senior-level AI security engineer at Carnegie Mellon's CERT Division developing machine learning-based prototypes and tools for AI security applications. Responsibilities include collaborating on experimental AI security solutions, supporting AI red teaming and adversarial ML initiatives, processing and analyzing cybersecurity datasets, and translating research concepts into operational capabilities. Requires BS (10 years), MS (8 years), or PhD (5 years) in CS, ML, cybersecurity, or related field with software engineering and containerization experience.

• AI Red Teaming
• MLSecOps
• Security Research

Director of Evaluations at LawZero, a non-profit developing safe-by-design AI systems. Lead the Evaluations Team (8-10 people) to design and execute comprehensive safety, capability, and adversarial robustness evaluations of the Scientist AI and frontier LLMs. Establish evaluation strategy and roadmap; design novel benchmarks and datasets measuring safety properties (honesty, goal-directedness, explainability); lead red-teaming programs to test resistance to jailbreaks, prompt injection, and data poisoning; develop evaluation infrastructure and tooling; publish technical reports and model cards; represent LawZero on AI safety measurement with external safety institutes.

• AI Red Teaming
• LLM Security
• Security Research

AI Security Researcher at Wiz focused on discovering and researching novel risks and attack vectors in cloud and AI-native architectures. Conduct deep technical research into modern cloud and AI environments, develop proofs of risk and technical POCs, and work with product and engineering teams to translate security research into product capabilities. Requires 5+ years hands-on security/research experience, proficiency with Python/Go scripting and security query languages, and preferred expertise in enterprise AI security risks.

• AI Red Teaming
• Security Research

Design and implement security controls for AI/ML systems, including LLM integrations and RAG pipelines. Identify and mitigate AI-specific threats such as prompt injection, model poisoning, and adversarial attacks. Develop guardrails and monitoring for anomalous AI behavior. Integrate AI security checks into CI/CD pipelines and conduct threat modeling. Ensure compliance with GDPR and financial regulations. Contribute to AI security standards and governance frameworks. Requires 3-5+ years in software/ML/appsec, hands-on AI/ML experience, Python proficiency, cloud platform expertise, and understanding of AI-specific security risks.

• LLM Security
• MLSecOps
• Security Research

4-month research fellowship focused on AI security. Participants work on empirical projects in AI security areas including adversarial robustness, red teaming, and vulnerability research under mentorship from Nicholas Carlini, Keri Warr, and other security-focused researchers. Past projects include AI agents discovering blockchain exploits and red team control evaluations. Requires strong Python skills, technical background, and preferably experience with pentesting, vulnerability research, or offensive security work.

• AI Red Teaming
• LLM Security
• Security Research

Engineering fellowship at AI safety and threat-intelligence company 10a Labs. Hands-on role combining applied research and engineering across red teaming, abuse detection, and AI system evaluation. Three concentrations available: Software Engineering (cloud infrastructure, testing, secure systems), Data Engineering (data sourcing, architecture, dashboards), or Machine Learning (model training, agentic systems, frontier model evaluation). Supports client-facing products and research initiatives in AI security and Trust & Safety.

• AI Red Teaming
• ML Engineering
• MLSecOps

Conduct deep technical research to discover novel risks and attack vectors in AI-native cloud architectures. Identify unaddressed risk areas through research and translate findings into product capabilities. Develop proofs of risk and technical POCs demonstrating impact and solutions. Work with product and engineering teams on risk coverage and new product scope. Requires 5+ years hands-on security research experience, specialized AI security knowledge, and strong scripting/query language skills.

• AI Red Teaming
• Security Research

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.

• MLSecOps
• Security Research

Lead the Machine Learning team at AIFT's Vulcan GenAI security platform. Translate cutting-edge security research on GenAI threats into production ML models powering blue-team guardrails and red-team vulnerability assessment. Own model development and fine-tuning (LLM architectures, LoRA/PEFT), MLOps infrastructure (CI/CD, data versioning, monitoring), and team leadership. Collaborate with security research and platform engineering teams to detect prompt injections, visual threats, and emerging AI attack vectors. Manage GPU resources and articulate technical trade-offs to leadership.

• LLM Security
• MLSecOps

LLM Security Evaluation Expert role at government solutions firm focused on rigorously testing security and integrity of Large Language Models. Responsibilities include designing sophisticated adversarial prompt attacks, testing model vulnerabilities, documenting security findings, and identifying model biases. Requires TS/SCI clearance and deep LLM knowledge combined with cybersecurity expertise. Emphasis on responsible adversarial testing practices to safeguard AI systems.

• AI Red Teaming
• LLM Security

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.

• Application Security
• LLM Security

Research Scientist on Anthropic's Frontier Red Team developing systems and frameworks for AI-empowered cybersecurity. Responsibilities include building tools for autonomous vulnerability discovery and patch development, designing experiments to evaluate AI cyber capabilities, constructing infrastructure for evaluating AI systems in security environments, and running purple-team simulations with AI defenders versus attackers. Work directly informs company and policy decisions on AI-enabled cyber threats.

• AI Red Teaming
• Security Research

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.

• Detection & Response
• LLM Security
• MLSecOps

Detect and investigate misuse of Anthropic's AI systems for cyber operations including malware development, social engineering, and influence operations. Develop abuse detection signals, create threat intelligence reports on LLM attack vectors, conduct cross-platform threat analysis, and implement systematic safety improvements. Build threat detection systems and maintain relationships with external threat intelligence partners.

• Detection & Response
• LLM Security
• Security Research

Build and ship Claude Security products that leverage frontier AI models for cybersecurity applications. Responsibilities include developing agent loops, tool integrations, and backend infrastructure for security products; collaborating with research teams to identify and develop new model capabilities for security use; and iterating based on user feedback. The role bridges research and go-to-market, requiring strong generalist engineering with technical depth in distributed systems, TypeScript, Python, or Go. Candidates with incident response, penetration testing, reverse engineering, or network analysis experience are preferred. This position requires 7+ years of software engineering experience.

• Application Security
• LLM Security
• MLSecOps

Hands-on security engineer focused on identifying and exploiting vulnerabilities in AI-enabled systems, LLM integrations, and agentic workflows across games and enterprise platforms. Responsibilities include adversarial testing of commercial and internal AI systems, prompt injection assessment, agent privilege escalation testing, and designing AI-driven security automation to scale red team and AppSec efforts. Reports to Application Security and Red Teaming organization.

• AI Red Teaming
• Application Security
• LLM Security

Research Engineer role focused on advancing AI model capabilities in secure coding, vulnerability remediation, and defensive cybersecurity through reinforcement learning. Responsibilities include designing and implementing RL environments, conducting security-focused experiments and evaluations, delivering work into production training runs, and collaborating with cybersecurity specialists. Requires domain expertise in cybersecurity combined with machine learning experience and strong software engineering skills. Ideal candidates have professional background in security engineering, fuzzing, detection and response, or applied defensive work.

• AI Red Teaming
• LLM Security
• Security Research

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.

• AI Red Teaming
• LLM Security
• Security Research

Detection and response engineer building solutions to monitor for threats, investigate incidents, and coordinate response efforts at Anthropic. Responsibilities include leading cybersecurity incident response across Anthropic's technology stack, developing novel tooling that may leverage Large Language Models to enhance detection and investigation capabilities, creating detections and workflows, optimizing incident response metrics, and working cross-functionally with security and engineering teams. Requires 3+ years software engineering experience or 5+ years detection/incident response experience, solid cloud environment knowledge, and strong collaboration skills.

• Detection & Response
• LLM Security

Senior security consultant role focused on AI/ML security architecture and design. Responsibilities include defining enterprise AI/ML security strategy, designing secure AI/ML models and pipelines across cloud platforms, leading adversarial testing and risk assessments, and embedding ethical AI governance. Works with major government and enterprise clients on securing advanced AI/ML systems against adversarial threats and compliance challenges.

• AI Red Teaming
• LLM Security
• MLSecOps

Build safety and oversight mechanisms for AI systems at Anthropic's Safeguards team. Develop monitoring and abuse detection systems for API partners, create intervention infrastructure, surface abuse patterns for model hardening, and build real-time multi-layered defenses. Work across three sub-teams: Safeguards Acceleration (agentic agent safety), Safeguards Interventions (detection and enforcement), and Safeguards Data Intelligence (distributed systems for threat detection at scale). Requires Python and TypeScript proficiency, software engineering background, and experience with integrity/abuse detection or adversarial inputs preferred.

• Detection & Response
• LLM Security
• MLSecOps

Develop ML systems to detect and mitigate misuse of AI products at scale. Build classifiers for harmful behavior detection, systems to identify coordinated attacks, threat models for agentic risks, and mitigations for prompt injection. Conduct research on automated red-teaming and adversarial robustness. Requires 4+ years ML/research engineering experience, Python proficiency, and familiarity with language models, anomaly detection, or adversarial ML.

• AI Red Teaming
• Detection & Response
• LLM Security

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.

• Governance & Compliance
• LLM Security
• MLSecOps

Conduct applied and theoretical research into GenAI vulnerabilities including adversarial attacks, prompt injection, jailbreaks, and data poisoning across multimodal systems. Develop AI security evaluation frameworks, datasets, and performance metrics. Design and evaluate mitigation strategies including fine-tuning, guardrails, and robust architectures. Publish findings in top-tier venues and integrate research into AI security products.

• AI Red Teaming
• LLM Security
• Security Research

Design, build, and operate production infrastructure powering Claude's safety systems. Own backend services on the token generation and sampling path, operate serving infrastructure across multiple deployment platforms (1P, AWS Bedrock, GCP Vertex), define and maintain SLOs, build observability and alerting systems, lead incident response for safety-critical infrastructure, and work with ML researchers to productionize new safety techniques into scalable production systems.

• Governance & Compliance
• MLSecOps

Research and engineering role within the AI Safety Institute's Safeguard Analysis Team, focused on developing and analyzing security interventions ('safeguards') for frontier AI systems. Responsibilities include assessing threats to AI systems, developing novel attacks against LLMs, building infrastructure for security evaluations, and red-teaming. The role combines research-oriented work (threat assessment, attack development) with engineering-oriented responsibilities (infrastructure development). Candidates should have experience in AI security, computer security, machine learning, red-teaming, LLM architecture and training, and production Python development.

• AI Red Teaming
• LLM Security
• Security Research

Threat Detection Researcher responsible for the full lifecycle of security detections in cloud-native environments, including threat research, data analysis, and production detection logic development. Designs behavioral baselines for complex cloud environments, expands detection engines with novel telemetry sources, conducts deep technical research into cloud services to uncover attack vectors, and investigates real-world attacks across cloud platforms and identity providers. Applies AI/LLM tools to enhance detection generation and telemetry analysis.

• Detection & Response
• LLM Security
• Security Research

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.

• Detection & Response
• Security Research

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.

• AI Red Teaming
• Detection & Response

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.

• AI Red Teaming
• MLSecOps
• Security Research

Build and scale AI-powered security analytics infrastructure at Anthropic's Detection Platform team. Design scalable data pipelines for processing security telemetry, develop ML-powered detection systems, and create innovative solutions leveraging Claude for security operations. Responsibilities include architecting detection and incident response capabilities, implementing security data pipeline infrastructure, and leading cross-functional security initiatives. Requires 7+ years software engineering experience with focus on security and data pipelines, strong cloud infrastructure knowledge, and ability to apply ML/AI to security problems.

• Detection & Response
• MLSecOps
• Security Research

Staff-level application security engineer at Anthropic responsible for designing and operating Claude-powered security systems. Focuses on LLM-driven code analysis, automated vulnerability remediation, and AI-assisted threat modeling. Leads secure design reviews for novel AI systems, manages bug bounty program with AI automation, and partners with product and infrastructure teams on security architecture for agentic systems. Owns end-to-end security systems including code execution sandboxing, agent identity/delegation, and tool-use boundary protection. Requires hands-on application security expertise, production coding ability, threat modeling skills, and experience securing AI/LLM-integrated systems.

• Application Security
• LLM Security
• MLSecOps

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.

• AI Red Teaming
• MLSecOps
• Security Research

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.

• Detection & Response
• Security Research