Member of Technical Staff – ML Research, Interpretability

About the role

We are looking for a Member of Technical Staff to join our ML Research team focused on interpretability. The role supports our mission to build a Large Physics foundation Model that can predict and control physical systems by uncovering causal structures.

Key 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 for debugging model failures and understanding rollout behavior.
• Partner with model, evaluation, and domain teams to translate interpretability findings into improved models and greater trust.

Required profile

• Strong grasp of machine‑learning fundamentals and modern neural‑network architectures.
• Passion for interpretability, representation analysis, or related research.
• Rigorous, hypothesis‑driven approach to understanding model behavior.
• Track record of turning open‑ended research questions into concrete findings.

Required skills

• Machine Learning
• Neural Network architectures
• Interpretability research