jobs

Enforcement Analyst, Agentic Alignment

About Anthropic Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers,

Company

Anthropic

Location

Boston, MA; San Francisco, CA; Seattle, WA; New York City, NY; Washington, DC

Status

Open

Posted

2026-10-25T02:29:23+00:00

Anthropic's Safeguards group is hiring an enforcement analyst to investigate cases where Claude agents behave harmfully or unexpectedly — reviewing transcripts, tool-use traces and code, then deciding on enforcement under the Usage Policy. The job mixes cyber assessment (scanning, exploitation, credential misuse, malicious code) with triage, case write-ups and building review pipelines that scale. Candidates need to read Python or JavaScript, have a security or threat-intelligence background, and have run structured investigations in trust and safety. On-call duty and exposure to disturbing content are stated.