Hoonkyung Cho
Software Engineer at NVIDIA
South Korea
Summary
🤩
Rockstar🎓
Top SchoolHoonkyung Cho is a software engineer with six years of experience specializing in autonomous driving perception, sensor signal processing, and multi-target sensor fusion. With roles at Hyundai, 42dot, and currently NVIDIA, he blends deep learning (TensorFlow, PyTorch, TensorRT, ONNX) with low-level C/C++ and Python engineering to move perception algorithms from research to in-car testing. His KAIST doctorate underpins strengths in lidar, radar, and camera pipeline design as well as object detection and data annotation workflows. Hoonkyung is adept at productionizing models for embedded platforms and coordinating cross-functional testing and documentation via Jira and internal wikis. He brings a practical researcher’s mindset—comfortable with both algorithmic innovation and hands-on signal-processing implementation—making him effective at turning complex sensor data into robust vehicle-ready perception stacks.
6 years of coding experience
3 years of employment as a software developer
박사, Electrical and Electronics Engineering, 박사, Electrical and Electronics Engineering at 한국과학기술원(KAIST)
Github Skills (34)
torchscript10
pytorch10
python10
jetson10
tensorrt10
machine-learning10
nvidia10
libtorch10
deep-learning10
self-attention10
gpu10
cuda10
backbone10
pre-trained-model9
numpy9
Programming languages (3)
Github contributions (5)
chohk88/dancetrack
Dec 2023 - Dec 2023
Contributions:13 pushes, 1 branch in 8 days
pytorch/TensorRT
Mar 2024 - Mar 2025
PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT
Contributions:90 reviews, 50 PRs, 74 pushes in 1 year
cudapytorchjetsonnvidiadeep-learning
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.