Yusik Kim
Researcher at IBM
France
Summary
🤩
Rockstar🎓
Top SchoolYusik Kim is a researcher and machine learning engineer based in France with four years of industry experience and a deep academic foundation including a Ph.D. in Operations Research from UC Berkeley. Currently at IBM, he blends research rigor with practical ML engineering from prior roles at Amazon, Spotify, and SAP, bringing experience across production systems and data science. He contributes to trusted AI tooling—most notably implementing and optimizing the RIPPER rule induction algorithm within the widely used AIX360 explainability framework—demonstrating a focus on interpretable ML. His background in mathematics and operations research informs a methodical approach to model interpretability and algorithmic refinement, making him as comfortable prototyping research ideas as shipping robust explainability components.
3 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy (Ph.D.), Operations Research, Doctor of Philosophy (Ph.D.), Operations Research at University of California, BerkeleyBachelor’s Degree, Mathematics and Statistics, Bachelor’s Degree, Mathematics and Statistics at Seoul National University
Dutch, French, Korean, English
Github Skills (13)
scikit10
machine-learning10
explainable-artificial-intelligence10
python10
ai10
scikit-learn10
deep-learning8
deeplearning-ai8
algorithms8
data-structures8
algorithm8
data-structure8
pandas7
Programming languages (3)
Github contributions (5)
Trusted-AI/AIX360
Jun 2022 - Oct 2022
Interpretability and explainability of data and machine learning models
Role in this project:
ML Engineer
ML EngineerContributions:15 commits, 4 PRs, 3 comments in 4 months
Contributions summary:Yusik primarily focused on implementing and refining the RIPPER (Repeated Incremental Pruning to Produce Error Reduction) rule induction algorithm within the AIX360 framework. This involved initial implementation, integration of the TRXF ruleset exchange format, and subsequent cleanup and optimization efforts. The user's contributions included developing the core RipperExplainer class, modifying the algorithm's internal workings, and updating the demo notebook to showcase the algorithm.
explainable-mlibm-research-aitrusted-aicodaitdeep-learning
kmyusk/AIX360
Jun 2022 - Nov 2022
Interpretability and explainability of data and machine learning models
Contributions:17 pushes, 7 branches in 4 months
interpretabilitydata-sciencedeep-learningmachine-learningexplainability
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.