Hyunkyun Moon
Heimdall - LLM Inference Platform
Seoul, South Korea
Summary
👤
Senior🎓
Top SchoolHyunkyun Moon is an ML platform engineer based in Seoul with 9 years of experience building cloud-native DBaaS and inference platforms, currently driving Heimdall — an LLM inference stack built on llm-d. He specializes in Kubernetes Operator patterns and has a strong track record delivering large-scale services (each serving 30,000+ VMs with 99.99% SLO) using Go and Python. Recent work focuses on inference optimization—e.g., a KV-cache prefix-aware gateway that achieved 20x TTFT improvement and tokenizer integrations that reduced per-request overhead. He consistently applies production-grade engineering: Helm deployments, kind-based e2e CI, and performance benchmarking alongside contributions to open-source projects like llm-d and vLLM. Known for reducing operational overhead through automation and resilient design, he also brings a practical knack for eliminating duplicate code and accelerating CI by 5x.
9 years of coding experience
Bachelor's degree Computer Science, Bachelor's degree Computer Science at Kyung Hee UniversityKorea Digital Media High School
Korean, English
Github Skills (23)
objective-c10
programming-language10
ios10
python10
swift10
macos10
development-environment9
xcode9
cocoapods9
carthage8
ide8
javascript8
vscode7
browser6
vscode-extension6
Programming languages (8)
Github contributions (5)
DB-Select/Baseball_for_Everyone
Jun 2018 - Sep 2019
Contributions:1 PR, 41 pushes, 11 branches in 1 year 3 months
GamePlatform/Campaign-Server
Jun 2017 - Sep 2019
Contributions:33 commits, 25 PRs, 32 pushes in 2 years 3 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.