← All roles

Member of Technical Staff — ML Research, Interpretability

Causal Labs· Research
Apply on company site
San Francisco, SingaporeFull-timePosted 2mo ago

About the role

Research position focused on interpretable ML within a Large Physics foundation Model project, aiming to understand and trust model predictions in physical systems through interpretability, representation analysis, and causal understanding.

Responsibilities

  • Probe the model's internal representations for physical quantities, structure, and conservation laws
  • Develop methods to explain individual predictions and the model's reasoning about interventions
  • Investigate whether interventions in the model's internal state produce physically coherent responses
  • Build tools and techniques for debugging model failures and understanding rollout behavior
  • Partner with model, evaluation, and domain teams to turn interpretability findings into better models and greater trust

Qualifications

  • Strong grasp of machine learning fundamentals and the internals of modern neural network architectures
  • Experience or strong interest in interpretability, representation analysis, or related research
  • Strong engineering skills for building interpretability tooling and running careful experiments
  • A rigorous, hypothesis-driven approach to understanding model behavior
  • A track record of turning open-ended research questions into concrete findings

Skills

Required:Machine Learning fundamentalsInterpretability and representation analysisEngineering for interpretability tooling
Last updated Oct 2, 2026. Interested? Apply on the company site.

About Causal Labs

Towards general causal intelligence

Causal Labs is building a Large Physics foundation Model (LPM) to learn causality through physics and weather

causalityphysicsweatherAIfoundation model
Company profileWebsite

More open roles at Causal Labs