Enforcement Analyst, Agentic Alignment

Anthropic•Washington, DC

1d•$245,000 - $285,000•Hybrid

About The Position

Anthropic is an AI safety and research company building reliable, interpretable, and steerable AI systems. The Enforcement Analyst, Agentic Alignment identifies and investigates harmful or unexpected model behavior and makes enforcement decisions. The role works with cross-functional partners, including Policy, Threat Intelligence, Engineering, Research, and Transparency, to support safe and beneficial AI as Claude takes on more autonomous work. The position may involve exposure to explicit, sexual, violent, or psychologically disturbing content. It also includes an on-call responsibility across the Policy and Enforcement teams. The analyst reviews agentic cases using transcripts, tool-use traces, and code; applies the Usage Policy to novel scenarios; documents decisions and precedents; and helps develop scalable review workflows. The role also analyzes cyber-related activity and case trends, communicates findings to varied audiences, and feeds enforcement insights back to policy, detection, and research teams. AI systems, including Claude, may be used to assist investigations and build lightweight tools. The role requires at least a bachelor’s degree or an equivalent combination of education, training, and/or experience, in a field relevant to the work as demonstrated through coursework, training, or professional experience. The annual salary range is $245,000–$285,000 USD. The position follows a location-based hybrid policy: staff are currently expected to be in an office at least 25% of the time, though some roles may require more. Anthropic sponsors visas, subject to role and candidate circumstances.

Requirements

Can read and understand code, such as Python, JavaScript, or shell scripts, well enough to follow what happened and why it matters.
Background in security, cyber threat intelligence, or a similar technical field that supports understanding cyber harm and judging its severity.
Experience in trust and safety, enforcement, investigations, or a related field, translating ambiguous policy questions and facts into defensible decisions and clear written findings.
Experience conducting structured investigations from first signal through final finding and judging when evidence is strong enough to act on.
Experience supporting or contributing to formal enforcement actions, including case documentation, evidence packaging, and escalation coordination.
Clear, concise writing and ability to present complex findings to Legal, Policy, and Engineering stakeholders, including non-technical audiences.
Sound judgment about when a case requires escalation and resilience when working with difficult content.
Bachelor’s degree or equivalent combination of education, training, and/or experience.
Relevant field of study, demonstrated through coursework, training, or professional experience.

Nice To Haves

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

Responsibilities

Review and investigate potential instances of Agentic Misalignment using transcripts, tool-use traces, and code.
Triage cases by severity and urgency and route them through appropriate channels.
Help operationalize review pipelines for agentic cases, turning detection leads and investigation findings into scalable, structured workflows.
Make and document consistent Usage Policy enforcement decisions in novel agentic scenarios and across surfaces.
Assess agentic cyber activity, including scanning, exploitation attempts, credential misuse, and malicious code, for potential real-world harm.
Write clear, well-evidenced case reports for enforcement peers and senior leadership.
Identify patterns and trends across cases and share findings with policy, detection, and research teams to improve policies, classifiers, and model behavior.
Maintain rigorous documentation of enforcement decisions, review logic, and precedents.
Collaborate with Threat Intelligence, Research, Engineering, and Policy partners to keep detection coverage current as agentic misuse and misaligned behavior evolve.
Use AI systems, including Claude, to assist investigations through transcript summarization, code analysis, data queries, and lightweight tooling.
Contribute to regular reports on agentic harm trends and enforcement outcomes.
Participate in on-call responsibilities across the Policy and Enforcement teams.