Dahjung Chung
Senior Software Engineer at NVIDIA
San Francisco Bay Area United States
Summary
🤩
Rockstar🎓
Top SchoolDahjung Chung is a Senior Software Engineer based in the San Francisco Bay Area with seven years of experience specializing in machine learning, computer vision, and deep learning, and a PhD in Electrical and Computer Engineering from Purdue. At NVIDIA he develops and optimizes real-time video analytics and object detection systems for crowded scenes, building on prior work in multi-camera tracking, face recognition, and re-identification. His contributions to NVIDIA-AI-IOT deepstream reference apps demonstrate hands-on expertise integrating and optimizing models with TensorRT and DeepStream for edge and data-center deployments. Dahjung’s academic research produced practical video-based health measurement and person re-identification algorithms, reflecting a blend of theoretical depth and product-focused engineering. He combines a strong publication-level research background with production experience shipping optimized C++/SDK solutions for demanding video inference pipelines.
7 years of coding experience
3 years of employment as a software developer
Bachelor's degree, electrical engineering, 3.65 / 4.3, Bachelor's degree, electrical engineering, 3.65 / 4.3 at Ewha Womans UniversityPh.D, Electrical and Computer Engineering, 3.78 / 4, Ph.D, Electrical and Computer Engineering, 3.78 / 4 at Purdue UniversityMaster's degree, electrical engineering, 4.16 / 4.3, Master's degree, electrical engineering, 4.16 / 4.3 at Yonsei University
Korean, English
Github Skills (10)
tensorrt10
c-language10
cprogramming-language10
machine-learning9
computer-vision9
cuda7
gpu-programming7
embedded6
sys6
ai6
Programming languages (2)
Github contributions (4)
NVIDIA-AI-IOT/deepstream_reference_apps
Mar 2019 - Aug 2019
Samples for TensorRT/Deepstream for Tesla & Jetson
Role in this project:
ML Engineer
ML EngineerContributions:33 commits, 30 pushes, 1 branch in 5 months
Contributions summary:Dahjung contributed to the development of deep learning inference applications, specifically focusing on integrating and optimizing models within the TensorRT and Deepstream frameworks. This is evident from the modifications to C++ code for network definition, engine creation, and inference execution for models like SE-ResNet50 and YOLO. Their contributions involved integrating anomaly detection capabilities and device type configuration for model deployment.
jetsondeep-learningdeepstreamtensorflowtensorrt
atonderski/lidarclip
Dec 2023 - Dec 2023
Contributions:2 comments in 1 day
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.