Description
Microsoft Red Team is hiring an AI Security Engineer focused on Cyber Capability Evaluation to design, implement, and operate offensive cyber-capability evaluations for frontier and agentic AI systems. The role builds realistic evaluation tasks, runs controlled experiments, analyzes model behavior, maintains cyber ranges and evaluation harnesses, and translates findings into security insights. Candidates need a relevant master's degree with at least one year of experience, or a bachelor's degree with at least two years of experience, plus programming, experimental, and cybersecurity skills. The position offers a typical U.S. base pay range of USD $102,100 to $202,200 per year, with higher ranges for the San Francisco Bay area and New York City metropolitan area.
