Researcher, Alignment CoT Monitorability
OpenAI· San Francisco
hybrid $295k – $500k / year seen live 1 day ago
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 , which training mechanisms affect monitorability, and
This link goes straight to the employer's ashby page. Posted 61 days ago.We last confirmed it was open 1 day ago.