Staff Software Engineer — Agent Evaluation Platform

Moveworks; Santa Clara, Northern (CA, KY); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Moveworks is seeking a Staff Software Engineer to own the evaluation platform for agent workflows. You will design and implement the judgement layer, calibration against human labels, and scalable infrastructure to score multi-step agent trajectories.

Deep expertise in backend systems (Python/Go), distributed execution, and observability is required. You will work on stateful simulations and a reusable orchestration harness at scale.

Qualifications

• 8+ 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.

Responsibilities

• Own the eval platform: orchestration, validation, and scoring for agent scenarios.
• Improve observability: OpenTelemetry data models, tracing, and dashboards.
• Develop stateful simulation environments with hermetic runs.
• Turn noisy agent behavior into a measurable signal for releases.
• Collaborate across teams to scale and reliability.

Skills

Python

Go

Distributed systems

Orchestration

OpenTelemetry

Async programming

gRPC

Tools

Temporal

Airflow

Argo

Job description

Moveworks is seeking a Staff Software Engineer to own the evaluation platform for agent workflows. You will design and implement the judgement layer, calibration against human labels, and scalable infrastructure to score multi-step agent trajectories.

Deep expertise in backend systems (Python/Go), distributed execution, and observability is required. You will work on stateful simulations and a reusable orchestration harness at scale.