jobs
Research Scientist, AI Safety and Alignment, DeepMind
As an organization, Google maintains a portfolio of research projects driven by fundamental research, new product innovation, product contribution and infrastructure goals, while providing…
Auf Englisch
- Company
- Location
- Seattle, WA, USA
- Status
- Open
- Posted
- 2026-11-13 08:08 UTC
A Research Scientist position in Google DeepMind’s Deep Understanding team, based in Seattle and on-site. The work covers empirical AI safety and alignment for large language and frontier models, including evaluation, steering, red teaming, safeguards, and mechanistic interpretability, with an emphasis on practical vulnerabilities in live systems over paper cycles. Candidates need a relevant PhD or equivalent experience, at least one year in AI safety/alignment/interpretability research, Python or C++ with JAX/PyTorch, and first-author ML conference publications.
Original job posting