AI Security Engineer

The Cloud & AI organization accelerates Microsoft's mission to secure digital technology platforms, devices, clouds, and AI systems across customers' heterogeneous environments and Microsoft's internal estate. Our culture is centered on a growth mindset, inspiring excellence, and helping teams and leaders bring their best every day. Microsoft Red Team (MRT) emulates real-world advanced persistent threats against Microsoft, external customers, and frontier AI systems. As AI systems become increasingly capable at reasoning, coding, tool use, exploitation, and autonomous execution, understanding when and how those systems materially increase offensive cyber capability is an important component of Microsoft's AI security mission. MRT Strategic AI is seeking an AI Security Engineer focused on Cyber Capability Evaluation. This is a hands-on technical role for implementing and executing evaluations of frontier AI models and agentic systems in realistic, controlled cyber environments. The engineer will work at the intersection of offensive security, AI agents, model evaluation, and experimental engineering to build and maintain evaluation tasks, run experiments, analyze model behavior, and determine whether observed results represent meaningful cyber capability, an evaluation artifact, or a limitation in the test environment. The role requires the ability to work independently within established technical direction, solve engineering and security problems, and contribute improvements to evaluation methods, cyber ranges, scoring, telemetry, and containment. The right candidate combines offensive-security experience with experimental discipline, programming skills, and an interest in emerging AI capabilities.

Design, implement, and operate offensive cyber-capability evaluations for frontier, preview, production, and open-weight AI models. Build and maintain realistic evaluation tasks covering vulnerability analysis, exploit development, application and system exploitation, attack-path reasoning, post-exploitation activities, and multi-step offensive workflows. Execute controlled experiments using AI models; define success criteria and baselines; collect reliable telemetry; and document results. Analyze model trajectories and investigate unexpected behavior to determine whether it reflects genuine capability, task leakage, environmental flaws, scoring errors, or other evaluation artifacts. Develop and maintain cyber ranges, vulnerable applications, exploit-development targets, and evaluation harnesses, and apply security controls for sandboxing, secrets management, telemetry, access, and containment when testing autonomous AI systems. Partner with red-team operators, researchers, engineers, and Responsible AI stakeholders to translate evaluation findings into security insights, and communicate results through reports, documentation, and briefings.

Minimum Qualifications: Master's Degree in Statistics, Mathematics, Computer Science, Computer Security, or related field AND 1+ year(s) experience in software development lifecycle, large-scale computing, threat analysis or modeling, cybersecurity, vulnerability research, and/or anomaly detection. OR Bachelor's Degree in Statistics, Mathematics, Computer Science, Computer Security, or related field AND 2+ years experience in software development lifecycle, large-scale computing, threat analysis or modeling, cybersecurity, vulnerability research, and/or anomaly detection. OR equivalent experience. Other Requirements: Ability to meet Microsoft, customer and/or government security screening requirements are required for this role. These requirements include, but are not limited to the following specialized security screenings: Microsoft Cloud Background Check: This position will be required to pass the Microsoft background and Microsoft Cloud background check upon hire/transfer and every two years thereafter. This role will require access to information