Wontak Ryu is an AI Software Engineer based in Seoul with 8 years of experience building production-grade ML systems across medical, manufacturing, and architecture domains. He specializes in MLOps and scalable inference—designing cost-efficient GPU architectures using Spot Instances, ArgoCD-driven CI/CD, Argo Workflows, and canary deployments to stabilize latency and reduce costs. His background spans research-grade model work (autoencoders, residual architectures, reinforcement inference) and hands-on optimization like TensorRT quantization, Triton Serving, and FastAPI/Golang service tuning. Notably, he built personalized Stable Diffusion pipelines for a consumer-facing AI photo app that learn from as few as 8–20 images, balancing privacy, safety, and operational reliability. Colleagues know him for turning complex research into reproducible, deployable pipelines and for pragmatic infrastructure choices that squeeze cloud costs without sacrificing performance.
Contributions:6 PRs, 187 pushes, 8 branches in 1 year 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.