Researcher, Alignment Interpretability

About this role

ABOUT THE TEAM The Interpretability team studies internal representations of deep learning models. We are interested in using representations to understand model behavior, and in engineering models to have more understandable representations. We are particularly interested in applying our understand

This is a short preview. Read the full description on Ashby before you apply.

• Research
• Alignment

Learn AI for this job, first module free

A short, hands-on course on using AI in this kind of work.

Start free