Biosecurity AI Safety Enforcement Analyst

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

Job summary

Anthropic Limited seeks an Enforcement Analyst focused on Bio Harms to protect against the misuse of AI systems, reading real model interactions and determining whether activity is benign research or a credible threat. You will enforce our Usage Policy with emphasis on bio risks, and own surveillance workflows across the bio-harms area.

You will collaborate with Policy, Threat Intelligence, Data Science, and Engineering teams to strengthen safeguards, handle time-sensitive escalations, and

Qualifications

• Hold a degree in a bio-related field or equivalent professional experience.
• Experience in Trust & Safety, content policy enforcement at platform scale.
• Experience using AI tools to develop dashboards and monitor metrics.
• Ability to analyze complex, ambiguous situations and make fast, defensible decisions under time pressure.

Responsibilities

• Enforce Usage Policies with a focus on detecting and mitigating bio risks and harmful use of AI systems.
• Take ownership of enforcement monitoring workflows for the bio-harms area, improving end-to-end detection, investigation, triage, and escalation processes.
• Monitor and analyze platform activity to identify emerging patterns related to biological threats that may require policy updates or enforcement action.
• Design and architect automated enforcement systems and review workflows that scale effectively while maintaining high accuracy.
• Conduct thorough investigations of potential violations, gathering and documenting evidence to support enforcement decisions.
• Proactively surface trends and propose improvements to detection methods and review workflows.
• Partner with Engineering and Data Science teams to optimize detection models and automated enforcement systems for bio-related policy violations.
• Partner with Policy and Threat Intelligence groups to understand potential exploits and contribute to risk‑assessment frameworks.
• Provide enforcement‑grounded feedback on policy gaps, and handle escalations and time‑sensitive situations related to potential bio‑related Usage Policy violations.

Skills

Trust & Safety

Policy enforcement

Data dashboards

Analytical thinking

Written communication

Time management under pressure

Education

Bio-related degree

Tools

SQL

Job description

Anthropic Limited seeks an Enforcement Analyst focused on Bio Harms to protect against the misuse of AI systems, reading real model interactions and determining whether activity is benign research or a credible threat. You will enforce our Usage Policy with emphasis on bio risks, and own surveillance workflows across the bio-harms area.

You will collaborate with Policy, Threat Intelligence, Data Science, and Engineering teams to strengthen safeguards, handle time-sensitive escalations, and