Product engineer, full stack

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:

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

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

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

You'll own problems end-to-end: talking to customers, defining what to build, building it, and iterating until it's great. This is not a role where you implement specs handed down.

Investigation interfaces: Design how engineers understand what their systems did and why. Long traces, tool calls, decisions, failures. How do you make a complex sequence of events legible in minutes?

Verification: Build the platform for verifying system changes: hosted simulated environments, trajectory replay, and monitors for unintended behavior changes.

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

The platform underneath: Work spaces, roles, permissions, billing, usage, and limits for teams running many workflows across many environments.

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 tinkerer's mindset with high agency - you find creative ways to overcome obstacles and ship

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