Product engineer, Agent

judgmentlabs; San Francisco (CA); On-site; USD 140,000 - 190,000; Full time

Job summary

Judgment is building the infrastructure for AI agents, delivering end-to-end production systems from data layers to UI. You will own the Judgment Agent workflow, verification environments, and UX to analyze large-scale production traces, with strong emphasis on customer-driven development and clear cross-functional communication.

You’ll design scalable interfaces and tooling that make complex agent behavior legible, enabling rapid iteration and robust deployment across teams and environments.

Qualifications

• Experience building and scaling end-to-end production systems from data layer to UI.
• Strong problem-solving skills in fast-changing, ambiguous environments.
• Builder mindset with high agency; ships solutions despite obstacles.
• Hands-on experience with LLMs or agents, or the drive to get there quickly.
• Comfort working directly with customers to understand needs and solve real-world problems.
• Excellent communication skills across technical and non-technical audiences.

Responsibilities

• Shape how the Judgment Agent runs large-scale investigations across thousands of production traces.
• Build the platform for verifying agent changes, including simulated evals and trajectory replay.
• Design interfaces to help engineers understand what their agents did and why, including long traces and decisions.
• Create swarm UX so engineers can monitor parallel investigations and steer findings.
• Develop workflows turning production trajectories into datasets, rubrics, and regression checks.
• Develop the platform underneath with workspaces, roles, billing, usage, and limits for multi-agent environments.
• Provide an SDK and terminal-first workflows enabling Judgment as a subagent during development.

Skills

End-to-end production systems

LLMs/agents experience

Customer collaboration

Problem solving in ambiguity

Builder mindset

Cross-functional communication

Job description

Product Engineer - Agents Job Description

The Role

Judgment is the learning infrastructure for AI agents. Agents in production don't improve from prompts alone. They improve from experience: the tasks they attempt, the mistakes they make, the edge cases they hit. Here’s how it works:

1. We ingest everything your agents do in production: traces, tool calls, decisions, outcomes

2. Judgment turns that raw experience into structured signals: failure modes, behaviors, rubrics, evals

3. Teams close the loop, shipping agent improvements validated against real production evidence

You’ll build the product experiences that make this loop legible, and you’ll build the agents that run it. This is not a role where you implement specs handed down. You’ll own problems end-to-end: talking to customers, defining what to build, building it, and iterating until it’s great.

What You Will Accomplish

• Judgment Agent: Shape how the Judgment Agent runs large-scale investigations: parallel investigators working across thousands of production traces, each covering a different dimension (failure modes, tool errors, regressions, drift), merging results into one answer.

• Verification: Build the platform for verifying agent changes: hosted simulated environments for stateful agent evals, trajectory replay against changed agents, and monitors for unintended behavior changes.

• Agent investigation interfaces: Design how engineers understand what their agents did and why. Long traces, tool calls, decisions, failures. What does debugging look like when the "program" is a reasoning loop? How do you make a thousand-step trajectory legible in minutes?

• Swarm UX: A hundred parallel investigations is useless if engineers can’t follow them. Design how humans watch a swarm work, redirect investigators that go down the wrong path, and consume findings without reading a hundred reports.

• The improvement loop: Build the workflows that turn production trajectories into datasets, judges, and regression checks, so the path from "found a problem" to "verified a fix" feels like one motion.

• The platform underneath: Workspaces, roles, permissions, billing, usage, and limits for teams running many agents across many environments.

• Judgment everywhere agents are built: An SDK and terminal-first experience so Claude Code, Codex, and OpenCode sessions can summon Judgment as a subagent mid-development.

What You’ll Bring

• Experience building and scaling end-to-end production systems, from data layer to UI

• Strong technical problem-solving skills, especially in fast-changing, ambiguous environments

• A builder and tinker’s mindset with high agency - you find creative ways to overcome obstacles and ship

• Hands-on experience building with LLMs or agents, or the drive to get there fast

• Comfort working directly with customers to understand their needs and solve real-world problems

• Excellent communication skills - clear, direct, and persuasive across technical and non-technical audiences