Wookie Park
Senior Research Scientist at NVIDIA
California, United States
Summary
👤
Senior🎓
Top SchoolWookie Park is a Senior Research Scientist based in California with 14 years of experience at the intersection of computer vision and machine learning, currently advancing research at NVIDIA. Trained at ETH Zurich and Imperial College London, he has led research teams in medical imaging at Lunit Oncology and contributed to foundational open-source projects like OpenCV and Theano/PyTensor. His work spans algorithm design, optimized C++ implementations (including SIMD optimizations for OpenCV’s xphoto and spatialGradient modules), and practical deep-learning model engineering for gaze estimation. Comfortable moving between prototyping research and production-grade performance tuning, he combines principled scientific rigor with pragmatic engineering to deliver robust image analysis systems. An uncommon strength is his history of improving test infrastructure and adding low-level performance tests, reflecting a focus on correctness and efficiency as much as novel models.
14 years of coding experience
8 years of employment as a software developer
Bachelor of Science - BS, Bachelor of Science - BS at Imperial College LondonDoctor of Science, Doctor of Science at ETH Zurich
Github Skills (26)
algorithm10
algorithms10
opencv10
c-language10
python10
image-processing10
testing10
machine-learning10
data-structure10
numpy10
deep-learning10
tensorflow10
data-structures10
computer-vision10
cprogramming-language10
Programming languages (8)
Github contributions (5)
swook/GazeML
Jun 2018 - Aug 2019
Gaze Estimation using Deep Learning, a Tensorflow-based framework.
Role in this project:
ML Engineer
ML EngineerContributions:17 commits, 3 PRs, 9 pushes in 1 year 2 months
Contributions summary:Wookie's commits primarily focused on refining and reimplementing the Deep Pictorial Gaze (DPG) model, a core component of the gaze estimation framework. They addressed comments and import statements and updated the model's architecture and training parameters. Additionally, they incorporated changes related to data augmentation and error message improvements for the model.
deep-learningmachine-learningestimationgaze-estimationtensorflow
opencv/opencv
Jun 2015 - Jul 2015
Open Source Computer Vision Library
Role in this project:Backend Developer
Backend DeveloperContributions:25 commits, 2 PRs, 12 comments in 13 days
Contributions summary:Wookie primarily contributed to the `spatialGradient` functionality within the OpenCV library. Their work involved adding a test class and a Sobel proxy method, integrating the new function into the `imgproc` module. They also added assertions and implemented an optimized, non-SSE version of the `spatialGradient` function and refactored the inner loop.
pythonvisiondeep-learningc-plus-pluscomputer-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.