Trust and Safety Intel Analyst, Model Behavior and Alignment

Google is hiring a Trust and Safety Intel Analyst, Model Behavior and Alignment (Washington, DC, on-site). The role sits on the Trust & Safety Intel Analysis team, which identifies and prioritizes threats such as deception, fraud, violent extremism, global events and system vulnerabilities, and owns the risk picture for unexpected or misaligned AI model behavior. Requires 7 years in areas such as intelligence or threat analysis, trust and safety, risk analysis, or AI safety and policy; Google says it welcomes applicants from intelligence and Trust & Safety backgrounds. Posted pay: $141,000–$205,000 per year plus bonus, equity and benefits. Apply through Google Careers.