Seungjun Nah
Senior Research Scientist at NVIDIA
California, United States
Summary
👤
Senior🎓
Top SchoolSeungjun Nah is a Senior Research Scientist at NVIDIA with 10 years of experience applying deep learning to visual quality enhancement, specializing in image/video deblurring, super-resolution, and large-scale generative AI. He holds a PhD in Computer Vision from Seoul National University and has a track record spanning academia and industry, including stints at Max Planck, Microsoft, and SNU. At NVIDIA he advances both model research and practical neural network acceleration, translating algorithmic innovations into optimized training pipelines. His open-source work includes contributions to the widely cited DeepDeblur project, where he implemented model architectures and CUDA half-precision support—an example of bridging cutting-edge research with production-aware engineering.
10 years of coding experience
3 years of employment as a software developer
Doctor of Philosophy - PhD Computer Vision, Doctor of Philosophy - PhD Computer Vision at Seoul National University
Github Skills (8)
neural-network10
cuda10
pytorch10
machine-learning10
convolutional-neural-networks10
deep-learning10
cudnn10
lua9
Programming languages (3)
Github contributions (5)
SeungjunNah/DeepDeblur_release
Dec 2016 - Sep 2020
Deep Multi-scale CNN for Dynamic Scene Deblurring
Role in this project:
ML Engineer
ML EngineerContributions:50 commits, 1 PR, 42 pushes in 3 years 9 months
Contributions summary:Seungjun primarily contributed to the model definition and training pipeline of a deep learning model for image deblurring. The commits involve modifications to the model architecture, including the definition of residual blocks, ResNet, and discriminator networks. The user also fixed bugs and added support for CUDA half precision training.
pytorchdeep-learningdeblurringmulti-scalescale
SeungjunNah/seungjunnah.github.io
Jan 2018 - Jan 2023
Contributions:113 commits, 111 pushes, 1 branch in 5 years
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.