AI Behavior Engineer

Highlights

• Build behavioral evaluations measuring how frontier AI systems act in deployment.
• Run rapid-turnaround evaluations for government and civil society partners.
• Design privileged-access evaluations and oversight exercises with frontier labs.

Ideal candidate

Hands-on evaluator who thrives turning ambiguous policy questions into shipped evidence fast. Low-ego communicator energized by working with domain experts and decision-makers for public-good AI oversight.

Requirements

• Hands-on experience designing and running AI evaluations, particularly behavioral or interactive evaluations
• Strong engineering instincts and good judgment about when good enough to ship is good enough
• Experience in customer-facing, consulting, or forward-deployed roles translating ambiguous needs into deliverables
• Experience running evaluations at scale or in a production context
• Ability to balance needs of AI researchers, domain experts, and senior decision makers
• Strong communication skills, low ego, openness to giving and receiving feedback