Minseo Kim
AI Solutions Engineer at Rebellions
Seoul, South Korea
Summary
🤩
Rockstar🎓
Top SchoolMinseo Kim is an AI Solutions Engineer based in Seoul with 10 years of hands-on experience building and optimizing machine learning inference systems. She has strong backend and performance engineering chops, exemplified by contributions to the high-profile OpenVINO open-source toolkit—adding ScatterElementsUpdate support, fixing YOLOv4 winograd issues, and improving performance and debugability. At Intel she delivered an Android multimodal AI assistant with LLM integration and engineered frame-accurate TTS-avatar sync and GPU-accelerated gesture recognition pipelines achieving 94% accuracy. Her background blends deep learning R&D with production engineering across startups and large firms, and she pairs a CS degree from Seoul National University with studies in psychology and international exchange experience. Colleagues describe her as a pragmatic problem-solver who enjoys cross-disciplinary collaboration and turning research prototypes into reliable products.
10 years of coding experience
2 years of employment as a software developer
Bachelor’s degree, Computer Science & Engineering, Bachelor’s degree, Computer Science & Engineering at 서울대학교 (Seoul National University)Université Paris CitéLund University
Github Skills (9)
opencl10
c-language10
inference10
cprogramming-language10
optimization10
ai9
deep-learning8
deeplearning-ai8
computer-vision8
Programming languages (3)
Github contributions (5)
openvinotoolkit/openvino
Feb 2021 - Nov 2022
OpenVINO™ is an open source toolkit for optimizing and deploying AI inference
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:1381 reviews, 44 commits, 646 PRs in 1 year 9 months
Contributions summary:Minseo primarily contributed to the OpenVINO toolkit by implementing and adding support for the `ScatterElementsUpdate` operation within the CLDNN backend, improving the toolkit's capabilities for AI inference. Their work involved modifying test cases, integrating this new operation, and optimizing performance. The user also addressed a Yolo v4 bugfix by modifying code related to winograd convolution, including its integration with the CLDNN library and improving its overall performance. Furthermore, they identified and fixed several code typos across the project and improved the error logs to enhance debugging and overall usability.
inference-enginepytorchmodel-optimizerdeep-learninggpu
isanghao/openvino
Jan 2021 - Apr 2025
OpenVINO™ Toolkit repository
Contributions:5 reviews, 2 PRs, 359 pushes in 4 years 2 months
pytorchdeep-learninggpuopenvino-toolkitcomputer-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.