Member of Technical Staff - Research, AI Safety
Vals · San Francisco · listed yesterday
About the role We are looking for an exceptional researcher to design and build the next generation of AI benchmarks for catching misaligned behavior in frontier models and agents, e.g., reward hacking, scheming, deception, loss of control, multi-agent safety, etc. You will create high-impact,…
Read the full description
Free registration — your contact details plus five quick fields about the role you want, or your CV — unlocks every description on the site, plus the apply link.
- The complete posting, as the employer wrote it
- Apply directly on Vals's own site
- A match score on every job, from your profile or your CV
