Andrew Kwangwoong Park
Software Engineer at Intel
Seoul, Korea, Republic of
Summary
🤩
RockstarAndrew Kwangwoong Park is a software engineer based in Seoul with five years of hands-on experience specializing in AI frameworks and backend/ML engineering. As an AI Frameworks Engineer at Intel, he contributes to high-impact open-source projects like OpenVINO, where he has implemented GPU-focused CUDA kernel ports and aligned detection output primitives across CLDNN and nGraph. He combines low-level performance tuning with practical deployment concerns, ensuring kernels compile cleanly and integrate with reference implementations. Comfortable working at the intersection of ML inference and systems programming, he brings both algorithmic insight and pragmatic engineering discipline. Notably, his contributions reveal a knack for translating legacy CUDA code (from Caffe) into modern, maintainable GPU kernels for production inference pipelines.
5 years of coding experience
Github Skills (7)
cuda10
computer-vision10
inference-engine10
c-language10
cprogramming-language10
ml9
machine-learning9
Programming languages (2)
Github contributions (5)
openvinotoolkit/openvino
Jul 2021 - Jan 2023
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:456 reviews, 36 commits, 147 PRs in 1 year 6 months
Contributions summary:Andrew's primary contribution involved adding a common comparator for the sorting function to align with other detection output primitives within the CLDNN and NGraph inference engine. The changes include modifications to the CUDA kernel and implementation for the detection output to the reference implementation. The commits also involve porting the CUDA kernel from Caffe to a new one for GPU. The user also added a fix for the compilation of the kernel.
inference-enginepytorchmodel-optimizerdeep-learninggpu
andrew-k-park/openvino
Feb 2021 - Apr 2025
OpenVINO™ Toolkit repository
Contributions:11 reviews, 14 PRs, 1879 pushes in 4 years 2 months
pytorchdeep-learninggpuopenvino-toolkitcomputer-vision
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.