Hyeonmin Kim is a GenAI specialist and AI lead based in Seoul with 10 years of experience building production-grade AI systems and cloud-native infrastructure. He designs and implements multi-agent LLM workflows using LangGraph, LangChain and Pydantic, and builds asynchronous FastAPI backends tied to observability-first LLMOps stacks (OpenTelemetry, Prometheus, Grafana, Tempo). At SmileShark he led AWS-based deployment pipelines (SageMaker, Bedrock, vLLM, Ray), retrieval pipelines and semantic chunkers, and presented at AWS Summit Seoul on scaling AI agents to automate ~80% of manual work. Now at NxtCloud, he focuses on operationalizing GenAI in enterprise settings, combining IaC, CI/CD and MLflow-driven traceability. Colleagues know him for pragmatic end-to-end delivery—translating research-grade components into resilient, monitored services—and for choosing lightweight open-source tools to solve large-scale document understanding problems.
Contributions:37 pushes, 1 branch in 3 years 8 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.
Request Free Trial
Hyeonmin Kim - GenAI Specialist AI Lead at NxtCloud