Safeguards Enforcement Analyst, Bio Harms

The role

You will enforce Usage Policies to detect and mitigate biological and CBRNE risks. You will investigate potential violations and improve enforcement monitoring workflows for bio-harms.

What you will do

• Enforce Usage Policies focusing on detecting and mitigating bio risks and harmful AI use.
• Take ownership of enforcement monitoring workflows for the bio-harms area.
• Monitor and analyze platform activity for emerging biological and CBRNE threats.
• Design and architect automated enforcement systems and review workflows.
• Conduct investigations of potential violations and document evidence.
• Proactively surface trends and propose improvements to detection and workflows.
• Partner with Engineering and Data Science to optimize detection models.
• Partner with Policy and Threat Intelligence to understand exploits and risk frameworks.
• Provide enforcement-grounded feedback on policy gaps.
• Handle escalations and time-sensitive situations related to bio-related violations.

Required qualifications

• Degree in a bio-related field (e.g., microbiology, molecular biology, biochemistry, public health) and/or relevant professional experience in a related field.
• Experience in Trust & Safety, content moderation, or policy enforcement at platform scale.
• Experience working with generative AI tools to refine and optimize content review and enforcement workflows.
• Experience in utilizing AI tools to develop data dashboards for metrics collection.
• Ability to analyze complex, ambiguous situations and make well-reasoned, defensible decisions under time pressure.
• Proactive and self-directed.
• Communicate clearly in writing and translate technical bio concepts for diverse audiences.

Nice to have

• Subject matter expertise in biodefense, biosecurity, WMD/CBRNE non-proliferation, or threat-intelligence.
• Understanding of adversary intent, acquisition and weaponization pathways, and dual-use concerns.
• Familiarity with cross-platform threat analysis and open-source intelligence (OSINT) techniques.
• Proficiency in SQL and/or other data analysis tools.
• Familiarity with dual-use research of concern (DURC), select agents, and relevant policy frameworks.

Benefits

• Competitive compensation and benefits
• Optional equity donation matching
• Generous vacation and parental leave
• Flexible working hours
• Office space

Before you apply

• You may be exposed to explicit content including material of a sexual, violent, or psychologically disturbing nature.
• The role carries a shared on-call responsibility across the Policy and Enforcement teams.
• Anthropic sponsors visas, but not for every role or candidate.

About the company

Anthropic is a public benefit corporation headquartered in San Francisco. Its mission is to create reliable, interpretable, and steerable AI systems.