Principal Security Research Manager (AI)

Location: Redmond, Washington, United States; 3 days per week in-office

Salary: USD $142,800–$274,800 gross annual base pay across the U.S.; USD $188,000–$304,200 in the San Francisco Bay Area and New York City metropolitan area.

Company

Microsoft Security is building agentic engineering systems for security triage, remediation, repository readiness, and scan-to-verified-closure workflows.

What you will do

• Design and build end-to-end evaluation harnesses for agentic security and engineering workflows.
• Create versioned benchmark suites and golden datasets covering normal, edge, adversarial, recovery, regression, and production-derived cases.
• Implement validators, automated graders, trace analyzers, result stores, comparison views, and workflow adapters.
• Measure task success, correctness, safety, policy compliance, latency, tool-call behavior, token usage, cost, and human-review effort.
• Integrate evaluations into engineering workflows, CI/CD, release gates, telemetry, and production feedback loops.
• Partner with agent builders, product teams, security engineers, data scientists, program managers, and leadership on release recommendations and autonomy-boundary decisions.

Requirements

• Doctorate with 3+ years, master's degree with 4+ years, bachelor's degree with 6+ years, or equivalent experience in computer science, computer security, statistics, mathematics, or a related field, together with relevant software, cybersecurity, threat analysis, vulnerability research, or anomaly detection experience.
• At least 1 year of people management experience.
• Production software engineering experience building systems, developer platforms, test infrastructure, automation frameworks, data pipelines, quality systems, or reliability tooling.
• Ability to design and implement evaluation systems end to end, including task definition, dataset creation, harness implementation, scoring, analysis, and operational integration.
• Strong coding, debugging, system design, operational excellence, and experience with structured data, logs, traces, metrics, APIs, automation workflows, and engineering telemetry.
• Experience with LLMs, AI agents, model evaluation, prompt and tool orchestration, automated grading, benchmark design, experimentation, statistical confidence, and regression analysis.

Nice to have

• Doctorate with 5+ years, master's degree with 8+ years, bachelor's degree with 12+ years, or equivalent experience in the relevant technical fields.
• Experience with security engineering, vulnerability management, SAST/SCA, SARIF, remediation workflows, secure development lifecycle, or compliance-sensitive systems.
• Experience with evaluator calibration and human-review protocols.

Culture & Benefits

• Growth mindset, respect, integrity, accountability, and an inclusive work environment.
• Benefits and additional compensation may be available depending on role eligibility.
• Applications are accepted on an ongoing basis until the position is filled, with the posting open for at least five days.