| Microsoft Careers

What you'll do

• Own the end-to-end delivery of runtime threat defense capabilities embedded directly into Copilot execution paths.
• Translate ambiguous agentic AI threat models into concrete engineering plans for detection and prevention mechanisms.
• Coordinate technical execution across security engineering, AI research, and platform teams to manage dependencies and risks.
• Define operability criteria for threat defenses, ensuring they are measurable, testable, and observable in production.
• Resolve complex technical and organizational tradeoffs where ownership boundaries are unclear and failure modes are novel.

What we're looking for

• Proven ability to lead execution in high-ambiguity environments with rapidly evolving requirements and threats.
• Strong background in security engineering, distributed systems, applied research, or ML systems.
• Experience delivering runtime detection, abuse prevention, or adaptive enforcement systems.
• Familiarity with agentic AI systems, LLM-based products, or non-deterministic execution environments.
• Solid track record of making sound technical tradeoffs and shipping durable solutions without heavy process.
• Demonstrated ability to translate research, prototypes, or threat models into production-grade systems.
• Experience partnering closely with offensive security or red-team functions.