Interpretability, Transparency, and Explanatory Systems

Mechanistic Interpretability Engineer

Career #82 · Domain 8

Summary

Analyzes internal model computations to identify how particular capabilities, concepts, errors, or risky behaviors arise.

Also relevant in

Artificial Intelligence
Professional, Scientific, and Technical Services
Cybersecurity

Full record coming soon

Detailed career records (responsibilities, pathways, AI collaboration, and more) follow our Standard Career Record format and will be published here over time. This page is a catalog entry for discovery only.