Enforcement Analyst: Agentic Alignment & AI Safety

Anthropic Limited; Boston, Washington (MA, District of Columbia); Hybrid; USD 245,000 - 285,000; Full time

Job summary

Anthropic Limited is seeking an Enforcement Analyst focused on Agentic Alignment to identify and investigate harmful and unexpected behavior by models, and to make enforcement decisions. You will work closely with Policy, Threat Intel, Engineering, Research, and Transparency teams to operationalize review pipelines and document reasoning for enforcement decisions.

You will engage with large datasets and transcripts, including exposure to sensitive content, and contribute to enforcement workflows

Qualifications

• Read and understand code (e.g., Python, JavaScript, shell) to follow what happened and why it matters
• Background in security, cyber threat intelligence, or a related technical field
• Experience in trust and safety, enforcement investigations, or a related field
• Structured investigations: build a case from first signal to final finding and know when evidence is strong enough to act
• Support or contribute to formal enforcement actions, including case documentation and escalation coordination
• Write clearly and concisely; present findings to Legal, Policy and Engineering audiences

Responsibilities

• Review and investigate potential instances of Agentic Misalignment from 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
• 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, logic, and precedents
• Collaborate with Threat Intelligence, Research, Engineering and Policy partners to keep detection coverage up to date
• Use Claude and other AI systems to accelerate investigations: summarizing transcripts, analyzing code, querying data
• Contribute to regular reports on agentic harm trends and enforcement outcomes

Skills

Read code (Python/JavaScript/shell)

Security/cyber threat intel

Trust & safety enforcement

Structured investigations

Case documentation & escalation

Clear written findings

Escalation judgment

Non-technical stakeholder comms

AI safety familiarity

Data analysis from transcripts/logs

Education

Bachelor's degree or equivalent

Job description

Anthropic Limited is seeking an Enforcement Analyst focused on Agentic Alignment to identify and investigate harmful and unexpected behavior by models, and to make enforcement decisions. You will work closely with Policy, Threat Intel, Engineering, Research, and Transparency teams to operationalize review pipelines and document reasoning for enforcement decisions.

You will engage with large datasets and transcripts, including exposure to sensitive content, and contribute to enforcement workflows