About the role

What you’ll do

• Investigate misuse and adversarial behavior across AI models, applications, and agentic workflows
• Translate investigative findings into platform safeguards, detection requirements, and operational improvements
• Partner with engineering, research, security, and integrity teams
• Assess incomplete or conflicting evidence and test competing hypotheses
• Communicate investigation findings and confidence levels
• Measure detection performance and validate mitigations against evolving adversarial behavior

What you’ll need

• Bachelor's degree and 8+ years of experience in product/program management, AI investigations, applied data science, trust and safety, or related disciplines
• Ability to meet Microsoft, customer, and/or government security screening requirements
• Strong command of AI and AI-assisted development tools, including command-line interfaces
• Hands-on experience investigating AI misuse, adversarial behavior, or AI safety/security incidents
• Applied data science experience using Python and SQL, Kusto, or comparable tools
• Experience translating investigations into shipped protections or operational improvements

Original job description