Senior Software Engineer, Agent Eval Platform

📋 Description

• Build the judgement layer of our agent evaluation platform, including rubrics, judges, calibration
• Anchor on one of three areas: eval orchestration, agent observability, or stateful simulation at
• Contribute to reliability, self-serve eval execution, and end-to-end orchestration across

🎯 Requirements

• 5+ years building production backend or infrastructure systems
• Strong in Python or Go (ideally both)
• Experience designing and operating systems that handle real traffic at scale
• Comfort turning non-deterministic agent behavior into measurable signals
• Experience with distributed systems, orchestration/workflow runtimes, observability, concurrency

🎁 Benefits

• Health plans, 401(k) with company match, ESPP, and family leave programs
• Flexible time away and generous leave policies
• Competitive compensation varies by location