Agentic Alignment Enforcement Investigator

Anthropic Limited; New York (NY); Hybrid; USD 245,000 - 285,000; Full time

Benefits offered by this job

Competitive compensation

Equity donation matching

Generous vacation and parental leave

Flexible working hours

Office in San Francisco

Job summary

Anthropic Limited is hiring an Enforcement Analyst focused on Agentic Alignment. You will identify and investigate harmful and unexpected model behavior, making enforcement decisions in collaboration with Policy, Threat Intel, Engineering, Research, and Transparency teams.

The role involves on-call duties and exposure to content that may be explicit or disturbing. You will work to operationalize review pipelines, document decisions, and help improve policy, classifiers, and model behavior as

Qualifications

• Read and understand code (e.g., Python, JavaScript, shell scripts) to follow events and significance.
• Background in security, cyber threat intelligence, or similar technical field.
• Experience in trust and safety, enforcement, investigations, or related field, translating policy questions into enforcement decisions.
• Conducted structured investigations from initial signal to final finding and justify actions.
• Experience supporting enforcement actions with case documentation and escalation coordination.
• Clear written communication to legal, policy, and engineering teams, including non-technical audiences.
• Judgment on escalation needs and resilience when handling difficult content.

Responsibilities

• Review and investigate potential Agentic Misalignment cases from transcripts, tool traces, and code.
• Triage cases by severity and urgency, sharing findings 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.

Skills

Code literacy

Security background

Enforcement investigations

Structured investigations

Policy & writing

Education

Bachelor's degree in a relevant field

Job description

Anthropic Limited is hiring an Enforcement Analyst focused on Agentic Alignment. You will identify and investigate harmful and unexpected model behavior, making enforcement decisions in collaboration with Policy, Threat Intel, Engineering, Research, and Transparency teams.

The role involves on-call duties and exposure to content that may be explicit or disturbing. You will work to operationalize review pipelines, document decisions, and help improve policy, classifiers, and model behavior as