jobs
Research Scientist, Mechanistic Interpretability, DeepMind
At DeepMind, we've built a unique culture and work environment where long-term ambitious research can flourish. We are seeking a highly motivated Research Scientist to join our team and contribute to…
En anglais
- Company
- Location
- London, UK
- Status
- Open
- Posted
- 2026-11-09 17:40 UTC
Full-time, on-site research scientist position at Google DeepMind in London. The person would set and lead research on mechanistic interpretability of large language models, including model self-conceptions, theory of mind, and social-media platform cognition. Work includes adapting interpretability methods to Gemini, designing experiments on internal vectors and mechanisms, collaborating with alignment teams, and publishing findings. The posting asks for a PhD or equivalent, three years of empirical AI research, PyTorch or JAX experience, LLM internals knowledge, and peer-reviewed publications. Cognitive science and philosophy of mind distinguish it.
Original job posting