Research Scientist, Mechanistic Interpretability
Google DeepMind · London, UK
Frontier labonsitesenior
At a glance
Highlights
- Investigate cognitive processes in large language models to advance safe AGI.
- Apply state-of-the-art interpretability techniques directly to Gemini models.
- Lead research on self-conceptions, theory of mind and metacognition in AI.
Ideal candidate
PhD-level researcher fascinated by minds, both human and artificial. You bridge technical ML with cognitive science and philosophy and want foundational interpretability work to shape safe AGI.
Requirements
- PhD in Computer Science, Mathematics, Physics or related technical field or equivalent research experience
- 3 years of experience designing, executing, and analyzing empirical research in AI
- Experience using machine learning frameworks such as PyTorch or JAX to run experiments
- Experience working with large language model architectures and internal representations
- Experience communicating scientific concepts to technical and non-technical audiences
- Publication record in mechanistic interpretability, AI safety, or machine learning in peer-reviewed venues
Lab profile
About Google DeepMind
Google's AI lab building frontier models like Gemini to advance science and general intelligence.
What they build
- Gemini
- Gemma
- AlphaFold
Known for
- Frontier foundation models and GenAI
- Large-scale training with JAX, PyTorch, TensorFlow
- Model evaluation and deployment expertise
- Responsible frontier AI research
Key facts
- Founded in 2010
- Headquartered in London, UK
- Part of Google (Alphabet)
First seen · Last seen