Skip to content

About the role

The team builds safety and oversight mechanisms for AI models handling biological information. The research engineer designs and runs evaluations, creates training data for safety classifiers, and iterates on these classifiers with ML engineers to ensure robustness against misuse while supporting legitimate research.

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

What the posting requires

Required
Preferred

Preferred experience: 8+ yrs

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.