💼 About This Role

You'll design model policies for high-risk cybersecurity domains at OpenAI, ensuring safe deployment of frontier AI. You'll translate cyber threat models into enforceable behavioral specifications and evaluation criteria. This role sits at the intersection of cybersecurity, AI safety, and policy implementation.

🎯 What You'll Do

• Design and maintain model policies for cybersecurity and frontier-risk domains.
• Translate cybersecurity threat models into behavioral specifications and evaluations.
• Analyze red-teaming results and deployment data to improve policy quality.
• Partner with safety researchers and engineers to operationalize policies.

📋 Requirements

• Strong technical expertise in cybersecurity (offensive, defensive, or vulnerability research).
• Experience building or applying threat models to complex technical systems.
• Ability to distinguish between legitimate security use cases and harmful assistance.
• Comfort using empirical evidence to inform policy decisions.

✨ Nice to Have

• Experience with dual-use or autonomous AI system risks.
• Strong systems thinking across policy and deployment safeguards.
• Written communication skills for technical concepts.

🎁 Benefits & Perks

• 💰 Offers Equity
• 🍽️ Three in-house prepared meals daily
• 🥤 Well-stocked kitchens with snacks and drinks
• 🏢 Private outdoor space and nap rooms
• 🚲 Private bike storage

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Call· 30 min
2. 2Technical Interview· 60 min
3. 3Onsite Interview· Half day