Anthropic · Builds reliable, interpretable, and steerable AI systems for safe, beneficial use
Open to people living in United States.
Listed location: Remote-Friendly, United States; San Francisco, CA | Washington, DC
Read from the posting text by our automatic check, which can be wrong. Confirm in the posting before you apply.
Designs and runs cyber-capability and safeguard-robustness evaluations for models, builds abuse-detection probes, and works with policy on detection.
This is a summary written by software from the company's posting. The posting is the source.