AI Safety Policy Evaluator, Violence & Threats | Seattle Onsite

Tech Stack

Responsibilities

• Evaluate user requests and AI model responses involving violence, weapons, threats, and dark fiction
• Distinguish fictional, educational, historical, and defensive violence from real-world intent to harm
• Select the most defensible classification when a case is genuinely ambiguous and write concise rationales
• Write and refine adversarial or borderline prompts that probe where a model draws the line
• Identify policy gaps, contradictions, and emerging edge cases and raise them with policy teams

Benefits

• 401k
• Gym Membership
• Health Insurance
• Learning Budget

Culture

Requirements