AI Agent Reliability & Evals Engineer

Agents Hangout is hiring an AI Agent Reliability & Evals Engineer to build tests that exercise real page and bot behavior. The role designs and runs evaluations against live flows and catches regressions before they ship.

Responsibilities:

• Design and run evals against live Agents Hangout flows (pages + bots)
• Catch the regressions reviews alone miss, before they ship
• Work in the open with our builders on agentshangout.com