ServiceNow
Tech Lead, Agent Eval Platform
Mountain View, CALIFORNIA, United States · Full-time · Posted Aug 26, 2026
- Experience
- 10+ years building production backend or infrastructure systems.
About the job
Tech lead building an agent evaluation platform that orchestrates scenarios, observes and traces agent behavior, simulates stateful enterprise systems, and turns evaluation results into signals for improving agents.
What you'll do
- Lead end-to-end delivery and other engineers across evaluation orchestration, agent observability, or stateful simulation.
- Build reliable, scalable systems for running, tracing, and comparing multi-step agent evaluations.
- Develop calibrated evaluation signals that can measure and help optimize agent behavior.
What they ask for
- 10+ years building production backend or infrastructure systems.
- Strong in Python or Go (ideally both), with experience operating systems handling real traffic at scale.
- Ability to tech lead engineers and end-to-end project delivery; good communication and soft skills.
- Experience in at least 3 listed areas: distributed systems; orchestration and workflow runtimes; observability internals; concurrent and async programming; data-intensive pipelines; or gRPC/protobuf service and interface design.
Tools
Python, Go, Temporal, Airflow, Argo, OpenTelemetry, gRPC, protobuf
AI focus
Builds evaluation methodology and calibrated judges for agent trajectories, with the goal of using evaluation signals to optimize agents.
Model-written summary · the original posting is authoritative