Machine Learning Engineer at 토스증권 (Toss Securities)
Seoul, South Korea
Join Prog.AI to see contacts
Join Prog.AI to see contacts
Summary
🤩
Rockstar
🎓
Top School
Hyogeun Oh is a Machine Learning Engineer with 7 years of experience focused on MLOps, Kubernetes-based AI infrastructure, and high-performance LLM serving. He has architected production-grade distributed training and serving systems—implementing GPU Direct RDMA, MIG, Triton, and a Model Context Protocol (MCP) to boost scalability and stability in enterprise and air-gapped environments. Hyogeun blends deep performance tuning (vLLM optimizations, speculative decoding, prefix-aware caching) with practical reliability work such as Prometheus/Redis/SSE observability and CI/CD automation that frees teams to focus on core problems. He values trust and predictability, sharing schedules transparently and building repeatable pipelines to minimize operational risk. An active community contributor and communicator, he runs a tech blog with 1,500+ MAU, spoke at PyCon Korea 2025, and participates in numerous study groups. Based in Seoul, he pairs academic research experience (SCI(E) Q1 publications) with hands-on engineering to squeeze peak performance from constrained resources.
7 years of coding experience
1 year of employment as a software developer
Master of Science - MS, Department of Mechanical Design and Production Engineering, Master of Science - MS, Department of Mechanical Design and Production Engineering at Konkuk University
Official implementations of PSENet, PAN and PAN++.
Contributions:4 PRs, 134 pushes, 9 branches in 1 year 9 months
onnxpanpppytorchscene-text-detectionstd
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.