| Microsoft Careers

What you'll do

• Own the model security roadmap to prioritize hardening strategies against OWASP LLM threats.
• Drive zero-day and exploit defense by evaluating and mitigating risks of models generating attacks.
• Build and scale red-teaming frameworks to continuously probe and improve model vulnerabilities.
• Partner with Microsoft Security product teams to ensure models meet real-world security needs.
• Define security-specific model evaluations focusing on practical usefulness for security practitioners.
• Shape security policy and readiness criteria for model launches, balancing capability and risk.
• Influence model training and architecture by embedding security considerations throughout development.

What we're looking for

• Bachelor's Degree and 5+ years of experience in product management, security engineering, or software development.
• Hands-on experience building, evaluating, or shipping ML-powered products or security tools.
• Deep familiarity with LLM security threats such as prompt injection, jailbreaking, and data exfiltration.
• Experience defining product requirements and driving decisions with researchers or ML engineers.
• Track record of building evaluation systems, security benchmarks, or adversarial testing frameworks.
• Ability to operate autonomously and drive projects from ambiguity to shipped outcomes.