Jade Cho is a Research Engineer based in Seoul with five years of hands-on experience in deep learning R&D and inference performance engineering. She has made notable open-source contributions to OpenVINO, optimizing GPU kernels, addressing CLDNN bottlenecks, and improving primitives like reduce fsv16 to boost inference efficiency. Comfortable working on backend systems and low-level performance tuning, she blends code refactoring and bug fixing with a deep understanding of AI inference internals. Jade's work reveals a penchant for squeezing extra performance from hardware through kernel tweaks and workgroup optimizations—skills that translate well to production ML deployment and edge inference use cases.
OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & Performance Engineer
Contributions:285 reviews, 40 commits, 120 PRs in 1 year 10 months
Contributions summary:Jade contributed to optimizing the OpenVINO toolkit, specifically focusing on the performance of inference engine components. Their work included optimizing the reduce fsv16 primitive and addressing performance bottlenecks within the CLDNN library. They also made improvements to GPU kernel functionality, including updates to kernels for various operations and adjusting local workgroup sizes for improved performance. The user's contributions involved code refactoring and bug fixes, demonstrating a deep understanding of the toolkit's inner workings and a commitment to improving its efficiency.
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.