💼 About This Role

You'll join the Safety Systems team at OpenAI, focusing on identifying and mitigating future AGI misalignment risks. You'll design worst-case demonstrations and rigorous evaluations to make these risks concrete and drive improvements. Your work will directly influence OpenAI's product launches and long-term safety roadmap.

🎯 What You'll Do

• Design worst-case demonstrations of AGI alignment risks
• Develop adversarial evaluations and system-level stress tests
• Create automated tools for scalable red-teaming
• Conduct research on failure modes of alignment techniques

📋 Requirements

• 4+ years in AI red-teaming or related safety fields
• Strong research track record (publications or high-impact work)
• Fluent in modern ML/AI techniques and large-scale codebases
• Clear communication with technical and non-technical audiences

✨ Nice to Have

• PhD or Master's in CS, ML, security, or related discipline
• Experience publishing influential papers
• Mentoring experience

🎁 Benefits & Perks

• 💰 Competitive compensation with equity

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

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