Safeguards Enforcement Analyst, Conventional Weapons

Detect and mitigate AI system misuse for conventional weapons and dangerous technology through enforcement workflows, content review, and policy development.
- Design automated enforcement systems and evals to assess model behavior, surface regressions, and inform policy improvements.
- Review flagged content to drive enforcement decisions, identify emerging misuse patterns, and escalate novel attack vectors.
- Partner with Engineering and Data Science to optimize detection systems and maintain enforcement guidelines and documentation.
- Requires deep expertise in weapons systems, policy enforcement or threat intelligence, and experience scaling content review workflows.
- Proficiency in SQL or Python, familiarity with generative AI products, and ability to assess technical plausibility of harmful content.

Anthropic is a frontier AI research and product company, with teams working on alignment, policy, and security. We post specific opportunities at Anthropic that we think may be high impact. We do not necessarily recommend working at other positions at Anthropic. You can read concerns about doing harm by working at a frontier AI company in our career review on the topic.