Researcher, Alignment CoT Monitorability
OpenAI · openai.com
brak informacji
llm
- Full-time
- On-site
- Mid
- San Francisco
ABOUT THE TEAM The CoT Monitorability team at OpenAI studies whether and when the chain-of-thought of frontier reasoning models is monitorable enough to support scalable oversight. We study how to measure monitorability https://openai.com/index/evaluating-chain-of-thought-monitorability/, which training mechanisms affect monitorability, and speculative methods to improve monitorability.…
Posted Aug 4, 2026
· Apply by Dec 7, 2026
Apply on OpenAI ↗
Opens the original posting on OpenAI