Researcher, Alignment CoT Monitorability

Responsibilities

• Design and run empirical studies of chain-of-thought monitorability across frontier reasoning models and training settings.
• Build evaluations to measure whether monitors can reliably predict properties of interest, including high-stakes misbehavior.
• Investigate how pre-training, synthetic data, reinforcement learning, and other interventions influence monitorability.
• Analyze model behavior and translate research findings into practical monitoring and oversight approaches.
• Collaborate with researchers and engineers across model training, alignment evaluations, and frontier-risk work.
• Produce externally publishable research to advance the broader science of alignment.

Requirements

• Strong empirical ML expertise with hands-on experience training, evaluating, or debugging large ML models (especially LLMs).
• Deep interest in AI alignment, interpretability, or model behavior.
• Ability to move from ambiguous research questions to concrete experimental setups and measurable results.
• Proficiency in moving between research ideation and engineering execution.

Preferred Qualifications

• Direct experience with chain-of-thought interpretability.
• Background in broader interpretability, alignment, or investigative model-behavior research.

Benefits

• Competitive salary ($250K – $445K) and generous equity.
• Comprehensive medical, dental, and vision insurance.
• 401(k) retirement plan with employer match.
• Paid parental leave and flexible PTO.
• Daily meals in the office and meal delivery credits.
• Annual learning and development stipend.
• Relocation support for eligible employees.

About the Company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of AI capabilities and seek to safely deploy them to the world through our products.