Malvern, Pennsylvania
•
Yesterday
What you'll do Build and debug LangGraph agent workflows.Extend the eval harness and run A/B tests between agent and prompt variants.Improve prompts with measured, regression-tested changes. - Extend human-agent interactive UI.Required LangGraph experience: state graphs, checkpointing, interrupts, tool-calling agents.LLM evals: golden sets, LLM-as-judge, A/B comparisons on quality, cost, and latency.Robust prompt engineering, including structured outputs.Python; Claude on AWS Bedrock a plus.Nice
Easy Apply
Contract
Depends on Experience



