Thomas Schmitt
Senior Machine Learning Engineer at Dailymotion
Paris, Ile-de-France
Summary
👤
Senior🎓
Top SchoolThomas Schmitt is a Senior Machine Learning Engineer based in Paris with nine years of hands-on experience building recommender systems and NLP solutions, and a decade-long research background rooted in a PhD on collaborative matching. He has led end-to-end recommender deployments at Dailymotion and Youboox, combining collaborative filtering, NLP embeddings and production tooling like Airflow and BigQuery. His open-source contributions include enhancing scikit-learn MOOC materials and implementing a MinHashEncoder for the dirty_cat ecosystem, showing a blend of pedagogy and practical encoder engineering. Earlier research work produced a Siamese neural approach to cold-start recommendation and earned a top-15 finish in the RecSys 2017 challenge. Comfortable moving models from notebook to production, he pairs rigorous academic training with pragmatic system design for large-scale content platforms. Colleagues value him for translating complex text-based machine learning research into reliable, deployable recommendation features.
9 years of coding experience
7 years of employment as a software developer
Master Thesis, MATHEMATICS AND STATISTICS, Master, Master Thesis, MATHEMATICS AND STATISTICS, Master at Ecole normale supérieureClasses Préparatoires (MPSI, MP*), Mathematics, Physics and Computer Sciences, Classes Préparatoires (MPSI, MP*), Mathematics, Physics and Computer Sciences at Lycée Albert SchweitzerMaster's degree, Mathematics and Computer Science, Master's degree, Mathematics and Computer Science at Paris-Sud University (Paris XI)Doctor of Philosophy - PhD, Machine Learning, Doctor of Philosophy - PhD, Machine Learning at Université Paris-Saclay
French, English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (15)
scikit10
data-preprocessing10
data-analysis10
pandas10
machine-learning10
dataprep10
python10
data-science10
scikit-learn10
numpy9
data-cleaning9
classification9
regression9
matplotlib8
pytest8
Programming languages (5)
Github contributions (5)
skrub-data/skrub
Oct 2019 - Aug 2020
Prepping tables for machine learning
Role in this project:
Data Scientist
Data ScientistContributions:29 commits, 6 PRs, 8 comments in 10 months
Contributions summary:Thomas primarily contributed to the development of the `MinHashEncoder` within the `dirty_cat` library. Their work focused on implementing and testing the `MinHashEncoder`, including refactoring the code, adding documentation, and fixing examples. The user also improved the code by including the `fast_hash` function and its associated unit tests.
autoencoderdata-preprocessingdatadata-sciencetabular-data
INRIA/scikit-learn-mooc
Jun 2020 - Oct 2020
Machine learning in Python with scikit-learn MOOC
Role in this project:Data Scientist
Data ScientistContributions:4 reviews, 7 commits, 13 PRs in 3 months
Contributions summary:Thomas contributed to the "Machine learning in Python with scikit-learn MOOC" repository by improving existing notebooks, particularly focusing on data exploration and model building. Their work involved modifying code, likely adding content related to the Adult Census dataset, and incorporating pandas profiling for data analysis. Furthermore, the user added slides, generating figures and visualizations with matplotlib, and implemented regression and classification models.
pythondata-sciencemachine-learningscikit-learnmooc
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.