Researcher, Alignment CoT Monitorability

Company hidden

San Francisco Full-time$295k–$500k / year Posted 30+ days ago

We were the first to show that chain-of-thought monitoring can be a practical additional safety mechanism, and today our monitoring systems are actively used on the company’s largest RL training runs to detect misbehavior. The issues we surface are then used to help improve our reward functions, environments, etc (without directly training against a CoT monitor). Our work sits in Alignment and intersects with model training, alignment evaluations, monitoring, and frontier-risk research.We care most about monitorability where the stakes are high, and about preserving useful oversight signals…

See the company and apply

Unlock to see who’s hiring, read the full description and apply on the company site.

Checking access…

See how well you match this job

Upload your resume and we’ll score your fit for this role — then tailor your CV to it with AI. Free, no credit card.

Check your match

Explore related jobs

Want more roles like this? Browse fresh jobs or tailor your resume with AI.