Explainable AI Postdoc: Interpretable ML Research

Lawrence Livermore National Laboratory invites applications for a Postdoctoral Researcher in Explainable AI in Livermore, CA. The role focuses on understanding how modern AI models learn and how to interpret their internal representations, including sparse decompositions and concept discovery.

The position supports human-in-the-loop workflows, rigorous evaluation of interpretability, and independent, collaborative ML research with national security applications. Hybrid work options expected.