Senior Software Engineer, Agent Evaluation Platform

Moveworks; Mountain View (CA); Hybrid; USD 161,000 - 274,000; Full time

Job summary

Moveworks is seeking a Senior Software Engineer to own the judgment layer of the Agent Eval Platform. You will design scoring, calibration, and validation for multi-step agent trajectories in enterprise environments.

You will build orchestration at scale, enhance observability with OpenTelemetry, and create stateful simulation environments to ensure reproducible runs. The role offers ownership across eval orchestration, observability, and simulation, with strong collaboration across teams.

Qualifications

• Five+ years building production backend or infrastructure systems.
• Experience designing and operating systems that handle real traffic at scale.
• Comfort turning fuzzy agent behavior into measurable signals.

Responsibilities

• Eval orchestration at scale: run end-to-end agent scenarios, collect transcripts and final state, and provide reliable scoring.
• Agent observability: implement OpenTelemetry-native traces and a robust data model for agent trajectories.
• Stateful simulation: manage fake enterprise systems with hermetic, repeatable per-run environments.
• Three-area ownership: choose one focus and contribute to the others as needed.
• Drive measurable improvements by turning eval signals into actionable feedback.

Skills

Distributed systems

Orchestration workflows

Observability

Async programming

Data pipelines

gRPC/protobuf

Python

Go

Tools

OpenTelemetry

Python

Go

Protobuf

Job description

Moveworks is seeking a Senior Software Engineer to own the judgment layer of the Agent Eval Platform. You will design scoring, calibration, and validation for multi-step agent trajectories in enterprise environments.

You will build orchestration at scale, enhance observability with OpenTelemetry, and create stateful simulation environments to ensure reproducible runs. The role offers ownership across eval orchestration, observability, and simulation, with strong collaboration across teams.