Researcher, Alignment CoT Monitorability

Highlights

• Study whether frontier reasoning models' chain-of-thought stays monitorable.
• Build evaluations measuring monitors' detection of high-stakes misbehavior.
• Translate findings into oversight for OpenAI's largest RL training runs.

What they offer

• Relocation assistance
• Equity

Ideal candidate

Empirical ML researcher with deep curiosity about alignment and model behavior, comfortable turning ambiguous questions into rigorous experiments and collaborating across teams to improve AI oversight.

Requirements

• Strong hands-on experience training, evaluating, or debugging large ML models, especially LLMs
• Depth in alignment, interpretability, model behavior, empirical ML, or adjacent research
• Can turn ambiguous research questions into measurable experiments and follow the evidence
• Move comfortably between research ideation and engineering execution
• Operate with high independence while collaborating closely across research and engineering teams