Model Policy Manager, Agentic Safety

Skills

About the Role

You will investigate how misaligned behavior emerges across long model trajectories and translate insights into behavioral policies, evaluations, monitoring, and safeguards. You'll build threat models, develop human data campaigns and gold sets, and partner with research, engineering, security, and product teams to inform deployment decisions.

Requirements

• Strong background in AI agent safety, privacy, security, cybersecurity, or adjacent fields
• Demonstrated interest in AI alignment
• Technical fluency to work with evaluation and training data
• Ability to translate ambiguous alignment risks into measurable evaluation criteria
• Clear communication about complex technical risks

Responsibilities

• Identify vulnerabilities as models interact with tools, data, and external systems and translate them into safeguards
• Develop threat models and empirical frameworks for harmful outcomes from misaligned behavior
• Identify underlying behaviors and system conditions that drive harmful outcomes
• Turn findings into policy frameworks, evaluation criteria, online measurement and safeguards
• Develop human data campaigns and gold sets
• Partner with research, engineering, security, and product teams
• Inform deployment decisions, system cards, and safeguards reports
• Build monitoring approaches that detect regressions and emerging risks

Benefits

• Equity
• Medical, dental, and vision insurance with HSA employer contributions
• Health FSA, Dependent Care FSA, and commuter pre-tax accounts
• 401(k) with employer match
• Paid parental leave, medical and caregiver leave
• Flexible PTO
• 13+ paid company holidays and office closures
• Mental health and wellness support
• Employer-paid basic life and disability coverage
• Annual learning and development stipend
• Daily meals in offices and meal delivery credits
• Relocation support
• Optional work from home on Thursdays and Fridays
• Charitable donation matching and wellness stipends