Jeongchul Kim is an ML Engineer based in Seoul with 11 years of experience building MLOps, inference platforms, and cloud-native AI services across startups and large telcos. He has led production deployments of NVIDIA Triton, vLLM, and custom NPU-backed inference stacks for recommendation, video, and LLM workloads while implementing CI/CD with GitHub Actions and ArgoCD. His background bridges research (peer-reviewed publications in IEEE, ACM, Springer venues) and hands-on platform engineering, having built monitoring, benchmarking, and API gateway systems with Grafana, Prometheus, Airflow and Kubernetes. At SAPEON and Toss he focused on scalable ML serving for ads, commerce and LLMs, and he drove early PoCs integrating Rebellions NPU cards into vLLM pipelines. A high-GPA graduate from Kookmin University, he pairs strong academic rigor with practical delivery—often producing end-to-end solutions from device/NPU integration to web and mobile demos.
Contributions:73 commits, 47 pushes, 1 branch in 2 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.