AI Safety Enforcement Analyst: Agentic Alignment

Anthropic Limited; San Francisco (CA); Hybrid; USD 245,000 - 285,000; Full time

Benefits offered by this job

Optional equity donation matching

Generous vacation and parental leave

Flexible working hours

SF office space

Job summary

Anthropic Limited is seeking an Enforcement Analyst focused on Agentic Alignment to investigate harmful model behaviors and make enforcement decisions. You will collaborate with Policy, Threat Intel, Engineering, Research, and Transparency teams, while handling on-call duties and content exposure.

The role emphasizes rigorous documentation and cross-functional collaboration. The position requires strong technical understanding, structured investigative ability, and a clear written communication

Qualifications

• Can read and understand code (Python, JavaScript, shell) to follow what happened and why it matters.
• Background in security, cyber threat intelligence, or a related technical field.

Responsibilities

• Review and investigate potential instances of Agentic Misalignment using transcripts, tool-use traces, and code.
• Triage cases by severity and urgency and communicate through appropriate channels.
• Operationalize review pipelines for agentic cases and translate leads into scalable workflows.
• Make enforcement decisions under the Usage Policy and document reasoning for each decision.
• Assess cyber-related agentic activity to determine real-world harm potential.
• Write clear, well-evidenced case write-ups for enforcement peers and leadership.
• Identify patterns across cases and feed findings back to policy, detection, and research teams.
• Maintain rigorous documentation of enforcement decisions and precedents.

Skills

Code reading

Security background

Investigations

Enforcement actions

Written communication

Judgment

Education

Bachelor's degree or equivalent

Field relevant to the role

Job description

Anthropic Limited is seeking an Enforcement Analyst focused on Agentic Alignment to investigate harmful model behaviors and make enforcement decisions. You will collaborate with Policy, Threat Intel, Engineering, Research, and Transparency teams, while handling on-call duties and content exposure.

The role emphasizes rigorous documentation and cross-functional collaboration. The position requires strong technical understanding, structured investigative ability, and a clear written communication