Conventional Weapons Safeguards Analyst for AI Safety

Society for AI Security; United States; Ibrido; USD 120.000 - 170.000; Tempo pieno

Descrizione del lavoro

Anthropic is seeking a Safeguards Enforcement Analyst focused on Conventional Weapons to mitigate misuse of AI in real-world harm. You will build and execute workflows to assess model behavior, drive enforcement decisions, and develop evaluative frameworks across complex policy areas.

You will work with cross-functional teams to detect policy violations, surface gaps, and update enforcement guidelines, while staying current on weapons trends and regulatory changes.

Competenze

• Bachelor’s degree in a relevant field or equivalent with hands-on enforcement experience.
• Experience translating complex policy and technical evidence into enforcement decisions.
• Experience standing up and scaling policy enforcement or content review workflows.

Mansioni

• Design and architect automated enforcement systems and scalable review workflows.
• Develop evals to measure model performance on policy areas and surface regressions.
• Collaborate with Engineering and Data Science to optimize detection and enforcement systems.
• Review flagged content to drive enforcement decisions and identify policy gaps.

Conoscenze

SQL proficiency

Python for data analysis

Policy enforcement experience

Threat intelligence

MITRE ATT&CK

Generative AI product experience

Content review workflows

OSINT techniques

Threat actor profiling

Enforcement design

Formazione

Bachelor’s degree or equivalent in a relevant field

Descrizione del lavoro

Anthropic is seeking a Safeguards Enforcement Analyst focused on Conventional Weapons to mitigate misuse of AI in real-world harm. You will build and execute workflows to assess model behavior, drive enforcement decisions, and develop evaluative frameworks across complex policy areas.

You will work with cross-functional teams to detect policy violations, surface gaps, and update enforcement guidelines, while staying current on weapons trends and regulatory changes.