Anthropic
Enforcement Analyst, Agentic Alignment
$245K–$285K
Boston, MA +5 · Full-time · Posted Oct 24, 2026
- Location
- Boston, MA
San Francisco, CA
Seattle, WA
New York City, NY
Washington, DC
San Francisco, California, United States - Experience
- Years required correlate with internal job level; no specific number stated.
- Education
- Bachelor’s degree or an equivalent combination of education, training, and/or experience; relevant field demonstrated through coursework, training, or professional experience.
- Visa sponsorship
- Visa sponsorship is available, but not for every role or candidate; if an offer is made, Anthropic will make every reasonable effort to obtain a visa.
About the job
Investigates potentially harmful or misaligned behavior by AI agents, makes Usage Policy enforcement decisions, and helps improve review workflows and safeguards.
What you'll do
- Investigate agentic cases using transcripts, tool-use traces, and code; assess severity and real-world harm.
- Make and document enforcement decisions, triage and escalate cases, and write evidence-based findings and reports.
- Improve scalable review workflows and feed case patterns back to Policy, Detection, Research, and Engineering teams.
What they ask for
- Can read code such as Python, JavaScript, or shell scripts to understand what happened and why it matters.
- Background in security, cyber threat intelligence, or a similar technical field.
- Experience in trust and safety, enforcement, investigations, or a related field, including structured investigations and formal enforcement actions.
- Clear writing and communication, sound escalation judgment, and resilience when working with difficult content.
Nice to have
- Demonstrated use of AI systems to accelerate work; comfort analyzing large volumes of data.
- Familiarity with AI safety and alignment, and interest in investigating novel agent behavior.
Pay
$245,000 — $285,000 USD annual base salary
Tools
Python, JavaScript, shell scripts, Claude
AI focus
Investigates harmful or unexpected behavior by increasingly autonomous AI agents and uses AI systems, including Claude, to accelerate investigations.
Model-written summary · the original posting is authoritative