2 days ago
Remote, United StatesSenior / Staff+
H1B sponsor
Base Salary
$102k - $261k/yr
Responsibilities
- Design, implement, and operate offensive cyber-capability evaluations for frontier, preview, production, and open-weight AI models.
- Build and maintain evaluation tasks covering vulnerability analysis, exploit development, application and system exploitation, attack-path reasoning, post-exploitation, and multi-step offensive workflows.
- Execute controlled experiments, define success criteria and baselines, collect telemetry, and document results.
- Analyze model trajectories and investigate whether results reflect genuine capability or evaluation artifacts.
- Develop cyber ranges, vulnerable applications, exploit-development targets, and evaluation harnesses with sandboxing, secrets management, telemetry, access, and containment controls.
- Partner with red-team operators, researchers, engineers, and Responsible AI stakeholders and communicate findings through reports, documentation, and briefings.
Requirements
- Minimum: master's degree in Statistics, Mathematics, Computer Science, Computer Security, or a related field plus 1+ year of relevant experience; or bachelor's degree in one of these fields plus 2+ years of relevant experience; or equivalent experience.
- Preferred: doctorate, or master's degree plus 3+ years of relevant experience, or bachelor's degree plus 5+ years of relevant experience, or equivalent experience.
- Programming ability, particularly in Python, including automation, scripting, or security tooling.
- Familiarity with large language models, generative AI systems, coding models, AI agents, model APIs, or model-evaluation frameworks.
- Experience with experimental methodology, controlled experiments, success criteria, result analysis, and technical documentation.
- Experience or exposure to security labs, cyber ranges, capture-the-flag environments, vulnerable applications, exploit development, vulnerability research, penetration testing, application security, or red teaming.
- Experience with coding agents, tool-using models, autonomous agent frameworks, or cyber-capability evaluations.
- Familiarity with PyRIT, adversarial-testing tools, containers, sandboxed execution, or cloud-based test infrastructure.
- Ability to meet Microsoft, customer, and government security screening requirements, including citizenship or protected-status verification for export-controlled and government-related work.
Benefits
- The typical U.S. base pay ranges from USD $102,100 to $202,200 for Security Research IC3 and from USD $119,800 to $234,700 for Security Research IC4, with different San Francisco Bay Area and New York City metropolitan area ranges.
- Applications are accepted on an ongoing basis until the position is filled, with the posting open for a minimum of five days.
- The role requires Microsoft background and Microsoft Cloud background checks upon hire or transfer and every two years thereafter.
- Certain roles may be eligible for benefits and other compensation.
About Microsoft
Microsoft develops operating systems, productivity software, cloud services, developer tools, and consumer devices for individuals, enterprises, and governments. Its main products include Windows, Microsoft 365, Azure, Visual Studio/GitHub, Xbox, and LinkedIn; revenue comes from software subscriptions and licenses, cloud consumption, hardware sales, and advertising. Founded in 1975 and headquartered in Redmond, Washington, Microsoft is a public company traded on Nasdaq.