Safeguards Enforcement Analyst, Conventional Weapons

The role

This person will detect and mitigate attempts to misuse AI systems to facilitate real-world harm involving conventional weapons and dangerous technology. They will build operational workflows, drive enforcement decisions, and develop evals across technical policy areas.

What you will do

• Design and architect automated enforcement systems and review workflows
• Develop and maintain evals to measure model performance
• Partner with Engineering and Data Science to optimize detection systems
• Review flagged content to drive enforcement decisions
• Support the Safeguards policy design team with structured feedback
• Develop and maintain enforcement guidelines and reviewer documentation
• Keep up to date with emerging weapons trends and regulatory changes
• Identify and escalate emerging misuse patterns and novel attack vectors

Required qualifications

• Deep, applied expertise in weapons systems
• Experience in policy enforcement, threat intelligence, counterterrorism, government, or a closely related field
• Direct exposure to harmful content, dangerous technology, or physical harm facilitation
• Experience standing up and scaling policy enforcement or content review workflows
• Proficiency in SQL and/or other data analysis tools
• Experience identifying emerging risks and threat actors
• Experience communicating findings to diverse stakeholders
• Experience working with generative AI products
• Experience writing effective prompts for content review and enforcement
• Understanding of the challenges involved in implementing product policies at scale
• Bachelor’s degree or an equivalent combination of education, training, and/or experience
• Field of study relevant to the role

Nice to have

• Subject matter expertise in conventional weapons and dangerous technology, autonomous systems, or critical infrastructure protection
• Familiarity with relevant legal and regulatory frameworks
• Experience developing evals or red-teaming AI systems
• Experience with threat actor profiling and threat intelligence frameworks (e.g., MITRE ATT&CK)
• Experience tracking threat actors, extremist networks, or misuse patterns across surface, deep, and dark web environments
• Experience with large language models
• Proficiency in Python for data analysis and workflow automation
• Background in law enforcement, national security, defense, counterterrorism, or a relevant regulatory environment
• Experience assessing the technical plausibility and real-world harm potential of content
• Familiarity with cross-platform threat analysis and OSINT techniques

Benefits

• Competitive compensation
• Optional equity donation matching
• Generous vacation
• Parental leave
• Flexible working hours
• Office space

Before you apply

• We do sponsor visas

About the company

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