Tech and design

Enforcement Analyst, Agentic Alignment

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

• Pay$245,000–285,000 per year
• WhereBoston, MA; San Francisco, CA; Seattle, WA; New York City, NY; Washington, DC
• Skills and toolsPython, JavaScript, Shell scripts, Code analysis, Transcript analysis, Data analysis, AI systems, Case documentation
• You’ll needBachelor's degree or equivalent experience, Relevant field of study, Security or cyber threat intelligence background, Trust and safety, enforcement, or investigations experience, Ability to work with difficult content
• AlsoOn-call responsibility; Explicit disturbing content
• ReferenceRef. 4943
• In the paper untilThu 19 Nov

About the job

AI safety enforcement analyst at Anthropic. $245–285k/year. Hybrid, with on-call responsibility. Investigate agentic AI behavior, assess potential harm, and make documented enforcement decisions. Requires a security or cyber threat intelligence background, investigations or trust and safety experience, and the ability to work with explicit, disturbing content.

This is our short summary. Read the full posting on boards.greenhouse.io.

Found on boards.greenhouse.io. Not placed by the employer; applications go to the original posting.