Paris, France · London, United Kingdom +1
Research Scientist/Engineer
Source verified: this exact posting was present on SaferAI’s careers feed on . View employer source →
The role
Develop threat models, select and run benchmarks on frontier AI models, analyze results and write risk reports. The role also supports safety mitigations and works with Inspect AI and model APIs. Paris, London or the San Francisco Bay Area are preferred; remote arrangements may be considered for particularly strong candidates. Numeric salary is not disclosed. Applications are rolling; see the employer page for full requirements.
Published by SaferAI on their own careers page and reproduced here unedited. Read it at SaferAI.
Apply at SaferAI → Applications go directly to SaferAI. This board does not sit in between, take a fee from you, or see your application.
What this listing does not tell you
Pay is not confirmed for this role. Check the employer’s posting for current compensation. Explore published bands from other roles →
SaferAI has 3 roles open on this board, 2 of them in evals and benchmarks.
Get the weekly AI Evals Jobs briefNew roles and board updates, with published pay where available. This is the general weekly brief. Or browse them all now.
Free. One email on Thursdays.
More roles like this
Matched by discipline, title, listed location and work arrangement.
Same discipline: Evals & Benchmarks · Shared listed location
Remote - Europe · London, United Kingdom +2Remote listed$195k – $262k
Same discipline: Evals & Benchmarks · Shared listed location
Amsterdam, Netherlands · Berlin, Germany +6$195k – $262k
Same discipline: Evals & Benchmarks · Shared listed location
Seattle, WA
Same discipline: Evals & Benchmarks
Palo Alto, CA$180k – $440k
Same discipline: Evals & Benchmarks