Joppe Geluykens
ML Solution Architect at Rubrik
Switzerland
Summary
🤩
Rockstar🎓
Top SchoolJoppe Geluykens is an ML Solution Architect with a decade of experience building end-to-end data science and machine learning solutions across banking, chemicals, FMCG, healthcare and media. Currently at Rubrik after a senior data scientist role at IBM, he combines consulting savvy with hands-on implementation to translate innovation into measurable business value. He brings strong academic foundations from KU Leuven (MSc Information Management, cum laude) and a BSc in Computer Science, plus the discipline of a competitive athletics background. An active contributor to the Ludwig low-code AI framework, his work on GBM support, integrated gradients explanations and compatibility fixes highlights a focus on robust model training and interpretability. Colleagues appreciate his taste for elegant, efficient architectures that integrate seamlessly into production environments.
10 years of coding experience
Bachelor of Science - BSc, Computer Science, Bachelor of Science - BSc, Computer Science at KU LeuvenHigh School, Mathematics-topsport, High School, Mathematics-topsport at Top Sports School Athletics - (Middle) Distance Running
Stackoverflow
1,862reputation
342kreached
4answers
0questions
tensorflow
top-5%
google-colaboratory
top-1%
Github Skills (20)
pytorch10
xai10
python10
data-science10
machine-learning10
explainable-artificial-intelligence10
trainings10
lightgbm10
google-colaboratory10
modeling10
tensorflow9
deep-learning9
llm7
natural-language-processing7
macos6
Programming languages (11)
Github contributions (5)
ludwig-ai/ludwig
Apr 2022 - Jan 2023
Low-code framework for building custom LLMs, neural networks, and other AI models
Role in this project:
ML Engineer / Data Scientist
ML Engineer / Data ScientistContributions:140 reviews, 76 commits, 120 PRs in 9 months
Contributions summary:Joppe primarily contributed to the development and improvement of the Ludwig AI framework, focusing on machine learning model enhancements. Their work included adding features for GBM (Gradient Boosting Machine) models, incorporating explanations using Integrated Gradients from captum, addressing issues related to model training, and improving backward compatibility. These contributions span model training, explanation, and general framework enhancements, suggesting a focus on core machine learning capabilities.
fairness-mlpythonframework-learningdeep-learning-frameworknatural-language-processing
jppgks/blog
Aug 2017 - Oct 2022
Personal website and blog
Contributions:8 PRs, 87 pushes, 6 branches in 5 years 2 months
reactnextjs
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.