Researcher, Recursive Self-Improvement Safety
- Locations
- San Francisco, California, United States · London, Greater London, United Kingdom
- Department
- Safety Systems
- Employment type
- Full-time
- Salary
- $380,000–$500,000 / year
- Posted
- about 2 months ago (Aug 7, 2026)
About the teamModels are becoming increasingly capable—moving from tools that assist humans to agents that can plan, execute, and adapt in the real world. Mitigating the frontier risks resulting from these capabilities is paramount to OpenAI’s ability to continue deploying models safely.The Preparedness team is dedicated to addressing these critical risks. Our work includes:Measurement.…