Tech Lead for Agent Evaluation Platform

Servicenow; Mountain View (CA); Hybride; USD 180 000 - 260 000; Plein temps

Résumé du poste

ServiceNow is seeking an experienced engineer to own the evaluation framework for AI agents within Moveworks. You will design rubrics and judges, orchestrate large-scale multi-turn scenarios, and build stateful simulators that enable reliable, reusable evals across enterprise environments.

You’ll work across distributed systems, orchestration runtimes, and observability, using Python or Go to implement scalable backend services, with a focus on measurable agent performance and safe, reproducible

Qualifications

• 10+ years building production backend or infrastructure systems.
• Experience in 3 of: distributed systems, orchestration/workflows, observability internals, async programming, data pipelines, gRPC/protobuf.
• Strong in Python or Go (ideally both).

Responsabilités

• Build the eval judgement layer for agent evaluation: rubrics, judges, calibration against human labels.
• Orchestrate end-to-end multi-turn agent scenarios at scale.
• Develop stateful simulators and isolated sandboxes for reproducibility.
• Enable self-serve eval workflows with reliable harness and rollout safeguards.

Connaissances

Python

Go

Distributed systems

Orchestration & workflows

Observability

Async programming

Data pipelines

gRPC/protobuf

Outils

Temporal

Airflow

Argo

Description du poste

ServiceNow is seeking an experienced engineer to own the evaluation framework for AI agents within Moveworks. You will design rubrics and judges, orchestrate large-scale multi-turn scenarios, and build stateful simulators that enable reliable, reusable evals across enterprise environments.

You’ll work across distributed systems, orchestration runtimes, and observability, using Python or Go to implement scalable backend services, with a focus on measurable agent performance and safe, reproducible