AISafetyResearch
Member of Technical Staff, Alignment
Foundation model lab (client name withheld under NDA)
San Francisco / London Full-time $380-540k + equity
Research and ship alignment techniques that gate every model release.
About the client
A foundation model lab with a dedicated alignment org that has genuine release authority.
What you'll do
- Run alignment and safety research end to end
- Build evaluations for deception, misuse and robustness
- Publish and contribute to external safety standards
- Work with policy and product on deployment decisions
What we're looking for
- Strong research background in ML, ideally alignment or interpretability
- Ability to implement, not just propose
- Publication record or equivalent evidence of research taste
- Genuine interest in safety as a discipline
Interview process
- 01Partner intro call
- 02Research screen
- 03Paper or project deep-dive
- 04Onsite and offer
Client names are withheld until a mutual NDA is in place. We never approach your current employer and never share your details without your written consent.