- Where
- Work mode not stated: New York, NY / San Francisco, CA · USANew York, NY / San Francisco, CA
- Level
- Early–Mid career, 1–9 yrsEarly–Mid1–9 yrs
- Pay
- $216k–$270k, top of range above $100k a year$216,000 – $270,000
- Apply by
- Rollingposted 28 Aug
- Hours and type
- Full-time
- Kind of work
- Research
- Added to CFI
- 28 August 2026
- Network
About the role
Researches AI agent robustness, control protocols and risk evaluations at Scale Labs, building test harnesses and finding exploits and mitigations. Findings inform governments, industry and the public on AI risk.
Summary of the employer's page written by AI. Check the full listing before you apply.
Requires
Ideally 3+ years of ML problem-solving experience; published ML research (preferred)
This role's deadline has passed, so it is no longer on the board. See open roles.