Researcher, Recursive Self-Improvement Safety

Skills

About the Role

You will help prepare for accelerated AI development that may culminate in recursive self-improvement. You will turn open-ended objectives into concrete research directions, build scrappy prototypes and iterate them into established components of safety pipelines, and work on scalable oversight, automated auditing, monitorability, model behavior science and verification. You will secure buy-in from colleagues, communicate clearly, and collaborate with or manage other staff as needed.

Requirements

• Exceptional technical execution
• Strong strategic and research taste
• Passion for mitigating risks of recursive self-improvement
• Bonus: prior work in ML research, AI alignment or AI verification

Responsibilities

• Consider future problems OpenAI might face and how to prepare for them
• Turn open-ended objectives into concrete research directions and prioritize the most useful work
• Build scrappy prototypes and iterate them into established components of safety pipelines
• Secure buy-in from other staff and communicate work clearly
• Collaborate with or manage other staff as needed

Benefits

• Equity
• Performance-related bonus
• 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
• Mental health and wellness support
• Employer-paid life and disability coverage
• Annual learning and development stipend
• Daily meals in offices and meal delivery credits
• Relocation support
• Charitable donation matching and wellness stipends