Yiheng Wang
Senior Software Engineer at NVIDIA
Shanghai, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolYiheng Wang is a Senior Software Engineer at NVIDIA specializing in medical deep learning and AI products for healthcare, with five years of experience bridging research-grade models and production systems. He has strong open-source credentials, contributing to MONAI (including VNet and subpixel convolution layers) and enhancing MONAI tutorials as an MLOps/back-end engineer. A former top Kaggle competitor (peak world rank 36) and Competitions Master, he brings practical expertise in segmentation, detection, and robust metric implementation. Prior roles span algorithm engineering for computer vision and video activity detection at WeWork and Pingan, including an ActivityNet podium finish. He holds a Master of Information Technology from the University of Melbourne and pairs technical rigor with endurance—having completed multiple certified full marathons.
5 years of coding experience
1 year of employment as a software developer
Bachelor of Engineering (B.E.), Bachelor of Engineering (B.E.) at Nanjing University of Posts and TelecommunicationsThe University of Melbourne
Japanese, English, Chinese
Github Skills (19)
pytorch10
convolutional-neural-networks10
data-pipelines10
python10
medical-image-processing10
model-driven10
model-building10
image-segmentation10
deep-learning10
segmentation10
ai10
pipe10
pipeline10
neural-network10
data-pipeline10
Programming languages (3)
Github contributions (5)
Project-MONAI/tutorials
Nov 2020 - Jan 2023
MONAI Tutorials
Role in this project:
Back-end Developer & MLOps Engineer
Back-end Developer & MLOps EngineerContributions:70 reviews, 52 commits, 74 PRs in 2 years 2 months
Contributions summary:Yiheng primarily focused on updating metric calculations and related code within the MONAI tutorial repository. Their work involved modifying and implementing new metrics across several notebooks and Python scripts, particularly in the context of segmentation tasks. The user updated training pipelines and implemented the necessary changes for the DynUNet and other models. Their contributions included creating new datasets, and integrating MONAI components.
pytorchmonai-tutorialsdeep-learningjupyter-notebookmonai
Project-MONAI/MONAI
Jul 2020 - Jan 2023
AI Toolkit for Healthcare Imaging
Role in this project:Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:374 reviews, 104 commits, 154 PRs in 2 years 5 months
Contributions summary:Yiheng's commits primarily focused on enhancing the `Convolution` class by adding a `groups` parameter and ensuring parameter names are used during initialization to prevent errors. They also moved the `project` variable to a parameter in the `Convolution` class. Further contributions include the implementation of the `VNet` model and a series of changes to other network architectures like `SENet` and `AHNet`, as well as adding a subpixel convolutional layer which suggests model development and improvement.
pytorchpythondeep-learningmedical-image-processingcomputer-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.