- Where
- Work mode not stated: Cambridge, MA / London / San Francisco, CA · USA, UKCambridge, MA / London / San Francisco, CA
- Level
- Mid–Senior career, 5–10+ yrsMid–Senior5–10+ yrs
- Pay
- $180k–$298k, top of range above $100k a year$180,000 – $298,000
- Apply by
- Rollingposted 24 Oct
- Hours and type
- Full-time
- Kind of work
- Research
- Added to CFI
- 24 October 2026
- Network
- Not listed
About the role
Builds automated red-teaming and evaluation methods that test the misuse risks of Lila's scientific AI models and the robustness of its safeguards. Also develops wider safety automation, working with risk researchers and mitigation engineers.
Summary of the employer's page written by AI. Check the full listing before you apply.
Requires
Empirical research or evaluation-software experience with modern AI systems
This role's deadline has passed, so it is no longer on the board. See open roles.