
product engineer, agent
Judgment Labs4 hours ago
Responsibilities
- Shape the Judgment Agent to run large-scale parallel investigations across production traces and merge findings into unified results.
- Build verification infrastructure including hosted simulated environments, stateful agent evaluations, trajectory replay, and monitors for unintended behavior changes.
- Design interfaces that help engineers understand agent traces, tool calls, decisions, failures, and long trajectories.
- Create swarm interfaces for monitoring, redirecting, and consuming findings from parallel investigations.
- Build workflows that turn production trajectories into datasets, judges, and regression checks.
- Develop platform capabilities for workspaces, roles, permissions, billing, usage, and limits across teams and environments.
- Build an SDK and terminal-first experience that lets Claude Code, Codex, and OpenCode sessions use Judgment as a subagent.
- Own product problems end-to-end through customer conversations, product definition, implementation, and iteration.
Requirements
- Experience building and scaling end-to-end production systems across the data layer and UI.
- Strong technical problem-solving skills in fast-changing and ambiguous environments.
- A builder and tinkerer mindset with high agency and a focus on overcoming obstacles and shipping.
- Hands-on experience building with LLMs or agents, or the ability and drive to develop that experience quickly.
- Comfort working directly with customers to understand needs and solve real-world problems.
- Excellent communication skills across technical and non-technical audiences.
Categories
About Judgment Labs
The continuous-improvement stack for agents. Monitor and improve your agent's behavior at scale.