Enforcement Analyst, Agentic Alignment (AI)

Location: Hybrid, with staff expected to work from one of the offices in Boston, San Francisco, Seattle, New York City, or Washington, DC at least 25% of the time; some roles may require more office time.

Annual salary: $245,000–$285,000 USD.

Company

Anthropic is an AI safety and research company building reliable, interpretable, and steerable AI systems.

What you will do

• Review and investigate potential instances of agentic misalignment using transcripts, tool-use traces, and code.
• Triage cases by severity and urgency, route them through appropriate channels, and make enforcement decisions under the Usage Policy.
• Operationalize scalable review pipelines for agentic cases and translate detection and investigation findings into structured workflows.
• Assess cyber-related agentic activity, including scanning, exploitation attempts, credential misuse, and malicious code, for real-world harm potential.
• Write evidence-based case reports, maintain rigorous documentation of decisions and precedents, and contribute to reports on agentic harm trends and enforcement outcomes.
• Collaborate with Threat Intelligence, Research, Engineering, Policy, and Transparency teams to improve detection coverage, policies, classifiers, and model behavior; use AI systems to summarize transcripts, analyze code, query data, and build lightweight tooling.

Requirements

• Ability to read and understand code such as Python, JavaScript, or shell scripts well enough to determine what happened and why it matters.
• Background in security, cyber threat intelligence, or a similar technical field, with the ability to understand cyber harm and assess its severity.
• Experience in trust and safety, enforcement, investigations, or a related field, translating ambiguous policy questions and facts into defensible enforcement decisions and clear written findings.
• Experience conducting structured investigations from the first signal to the final finding and determining when evidence is strong enough to act.
• Experience supporting or contributing to formal enforcement actions, including case documentation, evidence packaging, and escalation coordination.
• Clear and concise writing skills and the ability to present complex findings to Legal, Policy, Engineering, and non-technical stakeholders.
• Sound judgment about when to escalate a case and resilience when working with difficult content, including sexual, violent, or psychologically disturbing material.
• Bachelor’s degree or an equivalent combination of education, training, and experience in a field relevant to the role through coursework, training, or professional experience.

Nice to have

• Demonstrated use of AI systems to accelerate work and interest in finding additional applications.
• Comfort working with large volumes of data, including long transcripts, logs, traces, and complex multi-table datasets.
• Curiosity about AI agent behavior and interest in investigating uncategorized behavior and building approaches without established playbooks.
• Familiarity with AI safety, alignment, and current debates about the risks of increasingly autonomous AI systems.

Culture & Benefits

• Collaborative work across research, engineering, policy, threat intelligence, and other functions.
• Flexible working hours and a collaborative office environment.
• Generous vacation and parental leave.
• Competitive compensation, benefits, and optional equity donation matching.
• Visa sponsorship may be available; Anthropic makes reasonable efforts to support visas and works with an immigration lawyer.
• On-call responsibility across the Policy and Enforcement teams.