Principal Security Research Manager - Red Team

Microsoft•Redmond, WA

14h•$165,600 - $296,400

About The Position

Microsoft Security is seeking a founding technical leader to build and guide an AI red team spanning adversarial machine learning, agent security, offensive security, automation, and privacy. The role leads hands-on red teaming of advanced AI models, agentic systems, and AI-enabled security products; defines how attacks are designed, executed, and reproduced; and drives critical findings into durable improvements. It combines deep AI and security judgment with people leadership, partnering with researchers, engineers, product teams, and independent reviewers to reduce product risk and strengthen security assessments. The successful candidate will develop specialist talent, make sound severity decisions, and translate adversarial evidence into action. Microsoft’s mission is to empower every person and every organization on the planet to achieve more. The company emphasizes a growth mindset, innovation, collaboration, respect, integrity, accountability, and an inclusive work environment.

Requirements

Bachelor’s degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or a related field and 8+ years of related experience (e.g., statistics, predictive analytics, research); or a master’s degree in one of these fields and 6+ years of related experience; or a doctorate in one of these fields and 5+ years of related experience; or equivalent experience.
3+ years of people management experience.
Must be able to meet Microsoft, customer, and/or government security screening requirements, including passing the Microsoft Cloud Background Check upon hire or transfer and every two years thereafter.

Nice To Haves

Experience leading red-team programs and making evidence-based risk decisions across complex technical stakeholders.
Hands-on expertise in adversarial machine learning or offensive security, with demonstrated technical fluency across both AI systems and security operations.
Experience testing large language models, agentic systems, tool use, indirect prompt injection, or AI-enabled security products.
Experience hiring, coaching, and developing applied scientists, security researchers, or similarly specialized technical talent.
Ability to communicate technical findings, severity, and residual risk clearly to engineering teams and senior decision-makers.
Experience building a new technical function, hiring multidisciplinary talent, and establishing effective partnerships with independent security or governance teams.

Responsibilities

Build and develop a team of specialists spanning adversarial machine learning, agent security, offensive security, attack automation, and privacy.
Set the attack strategy and severity bar for uncovering critical weaknesses in advanced AI models, agentic systems, and AI-enabled products.
Lead hands-on red-team operations across models, training and evaluation systems, agent frameworks, tools, identities, and permissions to discover exploitable behavior before release.
Design and operationalize high-fidelity attack campaigns, continuous adversarial testing, and automated suites that reproduce realistic threats at scale.
Drive critical findings to verified remediation with research, engineering, and product security teams, converting recurring weaknesses into regression evaluations, adversarial environments, and stronger controls.
Produce clear, reproducible evidence that enables rapid severity decisions, focused engineering action, and efficient independent security review.
Track emerging AI attack techniques and real-world threat behavior, then evolve the team’s methods, tooling, and technical investments to stay ahead of them.