Staff Software Engineer, Agent Eval Platform

📋 Description

• Build the judgement layer of our agent eval platform.
• Develop eval orchestration at scale across multi-turn scenarios.
• Advance agent observability and tracing with OpenTelemetry.

🎯 Requirements

• 8+ years building production backend or infrastructure systems
• Strong in Python or Go (ideally both)
• Experience designing and operating large-scale systems
• Comfort turning fuzzy agent behavior into measurable signals
• Experience with distributed systems, orchestration, observability, concurrency