Skip to content

About the role

The Interpretability team works to understand how complex AI models function. This role involves building and maintaining the specialized infrastructure needed for this research. The engineer will optimize training and inference systems, and develop tools to help researchers experiment with model internals.

Our summary of the posting; the original is on the Anthropic careers page.

What the posting requires

Required
Preferred

These tags are our reading of the posting. They can miss something; the original posting is the reference.

Add your resume

Drop a PDF here, or

PDF or plain text, up to 10 MB.

Nothing is kept until you say so.