Safeguards Enforcement Analyst, Violence & Extremism
Core
Build and execute operational workflows to assess AI model behavior, drive enforcement decisions, and develop evals to mitigate misuse for violence, extremism, and dangerous technology.
Role type
Safeguards Enforcement Analyst (Violence & Extremism)
Builds
Automated enforcement systems, review workflows, and evals for AI safety
Domain
AI Safety / Counterterrorism / Threat Intelligence
Deliverable
production ML models | product features
Required skills
Policy enforcement, threat intelligence, SQL/data analysis, generative AI product experience, risk identification, stakeholder communication
Preferred skills
Weapons/dangerous tech expertise, legal/regulatory frameworks, red-teaming AI, threat actor profiling, OSINT, LLM technical understanding, Python
Technologies
SQL, Python, MITRE ATT&CK, LLMs
Responsibilities
Design automated enforcement systems and review workflows; Develop evals to measure model performance and surface regressions; Partner with Engineering/Data Science to optimize detection; Review flagged content to drive enforcement decisions; Support policy design with feedback on gaps; Develop enforcement guidelines and documentation; Track emerging misuse patterns and extremist activity
Seniority
Mid-Senior, hands-on IC
