Causal Labs
Member of Technical Staff — ML Research, Interpretability
San Francisco +1 · On-site · Staff · Full-time · Posted Jul 20, 2026
- Location
- San Francisco
Singapore
About the job
Investigate and explain the internal representations and behavior of physical-system models, using interpretability research to improve model performance and trust.
What you'll do
- Probe model representations for physical quantities, structure, and conservation laws; explain predictions and intervention reasoning.
- Test whether changes to internal model states produce physically coherent responses, and build tools to debug failures and rollout behavior.
- Work with model, evaluation, and domain teams to apply interpretability findings.
What they ask for
- Strong grasp of machine learning fundamentals and modern neural network architecture internals.
- Experience or strong interest in interpretability, representation analysis, or related research.
- Strong engineering skills for building interpretability tools and running careful experiments.
- Rigorous, hypothesis-driven approach and a track record of turning open-ended research questions into concrete findings.
AI focus
Interpretability research for physical-system AI models, including analysis of internal representations, predictions, interventions, and rollout behavior.
Model-written summary · the original posting is authoritative