Agentic Safety Enforcement Analyst

Vochure; United States; Hybrid; USD 245,000 - 285,000; Full time

Benefits offered by this job

Competitive compensation and benefits

Equity donation matching (optional)

Generous vacation and parental leave

Flexible working hours

Office space

Job summary

Anthropic is seeking an Enforcement Analyst focused on Agentic Alignment to identify and investigate harmful and unexpected behavior by models. You will work with Policy, Threat Intel, Engineering, Research, and Transparency teams to enforce the Usage Policy and document reasoning for each decision.

The role involves on-call responsibilities across Policy and Enforcement, and exposure to content spanning sensitive topics. You will help scale review workflows and compile enforcement reports.

Qualifications

• Bachelor’s degree or equivalent in a relevant field.
• Background in security or cyber threat intelligence.
• Experience in trust and safety, enforcement or investigations.
• Ability to translate policy questions into defensible enforcement decisions.
• Experience presenting complex findings to non-technical audiences.

Responsibilities

• Review and investigate potential instances of Agentic Misalignment from transcripts, tool-use traces, and code.
• Triage cases by severity and urgency and share through appropriate channels.
• Operationalize review pipelines for agentic cases, translating leads into structured review workflows.
• Make enforcement decisions under the Usage Policy and document the reasoning.
• Assess cyber-related agentic activity to determine real-world harm potential.
• Write clear, well-evidenced case write-ups for audiences from enforcement peers to senior leadership.
• Identify patterns across cases and feed findings back to policy, detection and research teams to improve models.

Skills

Code literacy

Security background

Trust and safety

Investigations

Written findings

Policy interpretation

Education

Bachelor's degree

Job description

Anthropic is seeking an Enforcement Analyst focused on Agentic Alignment to identify and investigate harmful and unexpected behavior by models. You will work with Policy, Threat Intel, Engineering, Research, and Transparency teams to enforce the Usage Policy and document reasoning for each decision.

The role involves on-call responsibilities across Policy and Enforcement, and exposure to content spanning sensitive topics. You will help scale review workflows and compile enforcement reports.