Product Engineer
Core
Build and ship product features for an AI agent evaluation platform, focusing on evals, replay, cohorts, and developer experience while engaging with the community to drive product decisions.
Role type
Product Engineer (AI Agents & Evaluation)
Builds
Production features for agent evaluation, replay systems, and developer tools
Domain
Artificial Intelligence / Large Language Models / Agent Frameworks
Deliverable
product features
Required skills
Python, Agent Frameworks (LangGraph), Evaluation Systems, Trace Data/Observability, Developer Tools/SDKs/APIs, Open-source contributions, Public technical communication
Preferred skills
LLM observability platforms, Production ML infrastructure
Technologies
Python, LangGraph
Responsibilities
Build and ship features across evals, replay, cohorts, and developer experience; Create in public on X and GitHub to engage the AI engineering community; Engage with target users (AI agent builders, eval practitioners); Close the loop between community feedback and product decisions
Seniority
Mid-level, hands-on IC
