Conventional Weapons Safeguards Architect

EngineersOfAI; New York, Northern (NY, KY); Hybrid; USD 120,000 - 180,000; Full time

Job summary

Anthropic is seeking a Safeguards Enforcement Analyst focused on Conventional Weapons. You will detect and mitigate attempts to misuse AI systems, build scalable enforcement workflows, and develop evaluations across technical policy areas.

The role requires handling potentially graphic or disturbing content in a controlled environment. Ideal candidates bring deep weapons systems expertise, policy enforcement experience, and strong data analysis skills, with the ability to collaborate across

Qualifications

• Deep knowledge of weapons systems and ability to translate evidence into enforcement decisions.
• Experience in policy enforcement, threat intelligence, or counterterrorism with exposure to harmful content or dangerous technology.
• Experience standing up and scaling policy enforcement or content review workflows.
• Proficiency with SQL or similar data analysis tools to draw insights from large datasets.

Responsibilities

• Design and architect automated enforcement systems and scalable review workflows with high accuracy.
• Develop and maintain evals to measure model performance on policy areas and surface regressions.
• Collaborate with Engineering and Data Science to optimize detection and enforcement systems for policy violations.
• Review flagged content to drive enforcement decisions and identify policy gaps.
• Support policy design by providing feedback on enforcement ambiguities based on real scenarios.
• Develop and maintain enforcement guidelines and reviewer documentation for consistent enforcement.
• Stay updated on weapons trends, regulatory changes, and enforcement best practices.

Skills

Weapons systems expertise

Policy enforcement

Threat intelligence

Data analysis

Cross-functional communication

AI policy experience

Tools

SQL

Job description

Anthropic is seeking a Safeguards Enforcement Analyst focused on Conventional Weapons. You will detect and mitigate attempts to misuse AI systems, build scalable enforcement workflows, and develop evaluations across technical policy areas.

The role requires handling potentially graphic or disturbing content in a controlled environment. Ideal candidates bring deep weapons systems expertise, policy enforcement experience, and strong data analysis skills, with the ability to collaborate across