AI Security Engineer
$102k - $202k • United States, Multiple Locations, Multiple Locations • Full-time
Posted 1mo ago
About the job
Microsoft Red Team (MRT) is seeking an AI Security Engineer focused on Cyber Capability Evaluation. This role involves implementing and executing evaluations of frontier AI models and agentic systems in realistic, controlled cyber environments. You 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. The position requires independent problem-solving, contributing to evaluation methods, cyber ranges, scoring, telemetry, and containment, and combining offensive-security experience with experimental discipline, programming skills, and an interest in emerging AI capabilities.
Responsibilities
- Design, implement, and operate offensive cyber-capability evaluations for AI models.
- Build and maintain evaluation tasks covering vulnerability analysis, exploit development, and offensive workflows.
- Execute controlled experiments using AI models, define success criteria, collect telemetry, and document results.
- Analyze model trajectories and investigate unexpected behavior to determine genuine capability or evaluation artifacts.
- Develop and maintain cyber ranges, vulnerable applications, and evaluation harnesses.
- Partner with stakeholders to translate evaluation findings into security insights and communicate results.
Requirements
- 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.
- Ability to meet Microsoft, customer and/or government security screening requirements.
- Programming ability.
