Safeguards Enforcement Analyst, Violence and Extremism

• Build workflows to assess AI model behavior and identify misuse attempts in violence and extremism.
• Architect automated enforcement systems and review workflows that scale while maintaining high accuracy.
• Develop evals measuring model performance and identifying regressions to inform policy improvements.
• Review flagged content to drive enforcement decisions and surface emerging misuse patterns and gaps.

This role directly prevents AI-enabled violence and extremism by building systems to detect and mitigate misuse, ensuring AI technologies are used safely and ethically.

• Experience in trust and safety, content moderation, or enforcement operations.
• Strong analytical skills to identify misuse patterns and emerging threats.
• Ability to design scalable workflows and automated systems.
• Knowledge of extremist movements and regulatory landscape.

Competitive compensation and benefits package. Specific details not provided.

Anthropic is an AI safety company dedicated to building reliable, interpretable, and steerable AI systems. They focus on ensuring AI benefits society and avoids catastrophic risks.