Kyunam Cho

Affiliated Professor

Seoul, South Korea
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Kyunam Cho is an AI/ML systems software architect and affiliated professor in Seoul with over two decades of experience building large-scale cloud and HPC platforms for machine learning, deep learning, and data science. He combines deep expertise in multi- and many-core programming, hardware acceleration (GPGPU, Xeon Phi), and distributed training with practical leadership roles at Samsung, HyundaiCard, and LG Uplus. Kyunam has driven container-based, enterprise-wide ML/AI platforms and recently translated that systems knowledge into academic and research appointments while pursuing a PhD in computer science. Comfortable moving between low-level performance optimization and high-level cloud architectures, he is as fluent in GPU kernels as he is in productionizing models across an organization. An unusual strength is his long-running focus on both edge hardware capabilities and cloud-scale orchestration, enabling optimized end-to-end ML deployments.
code12 years of coding experience
job22 years of employment as a software developer
bookPhD candidate Computer Science, PhD candidate Computer Science at Korea University
book공학학사 기계 설계 및 기계 설계 CAD/CAM, 공학학사 기계 설계 및 기계 설계 CAD/CAM at Chung-Ang University
languagesEnglish, Chinese
github-logo-circle

Github Skills (19)

model-compression9
nas9
hyperparameter-tuning8
neural-architecture-search8
automated-machine-learning8
machine-learning-algorithms8
feature-engineering8
pytorch7
automl7
parameter-tuning7
machine-learning7
python7
deep-reinforcement-learning7
hyperparameter-optimization6
mlops6

Programming languages (2)

C++Python

Github contributions (5)

github-logo-circle
mystous/gpu_scheduler

Feb 2024 - Jul 2026

Contributions:161 pushes, 3 branches, 1 comment in 2 years 5 months
mystous/vllm_hybrid

Aug 2025 - Jun 2026

A high-throughput and memory-efficient inference and serving engine for LLMs
Contributions:1 PR, 281 pushes, 10 branches in 10 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