Selim Raboudi
Data Lead
Paris, Ile-de-France
Summary
👤
Senior🎓
Top SchoolSelim Raboudi is a Data Lead based in Paris with 11 years of experience operating at the intersection of education and technology. He brings a strong engineering foundation in information theory and signal processing (IMT Atlantique) and hands-on AI exposure from an exchange at KAIST, which he pairs with instructional design training to build data-driven learning products. At Didask he leads data efforts, focusing on robust data preparation and model input pipelines—work reflected in open-source contributions to Vowpal Wabbit where he improved data conversion utilities to handle large, complex feature sets and tagging. His background in dance education and cultural work signals a rare blend of technical rigor and creative pedagogy, informing pragmatic, learner-centered analytics. Colleagues can expect a leader who moves seamlessly between low-level data engineering and applied ML for educational impact.
11 years of coding experience
Telecom Bretagne, MS Engineering, Information Theory, Signal Processing, Telecom Bretagne, MS Engineering, Information Theory, Signal Processing at IMT AtlantiqueBachelor's degree, Educational/Instructional Media Design, Bachelor's degree, Educational/Instructional Media Design at OpenClassroomsPasseur Culturel en Danses Hip Hop, Drama and Dance Teacher Education, Passeur Culturel en Danses Hip Hop, Drama and Dance Teacher Education at Centre de Formation de Danse de CergyPreparatory School, Advanced Mathematics, Physics and Chemistry, Preparatory School, Advanced Mathematics, Physics and Chemistry at Lycée MassénaExchange Student, Artificial Intelligence and Computer Networks, Exchange Student, Artificial Intelligence and Computer Networks at Korea Advanced Institute of Science and Technology
English, French, Arabic, Spanish, Korean
Github Skills (10)
data-preprocessing10
machine-learning10
c-language10
dataprep10
cprogramming-language10
r10
elearning9
bandit8
searching8
active-learning8
Programming languages (7)
Github contributions (5)
VowpalWabbit/vowpal_wabbit
Apr 2015 - Oct 2015
Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive learning.
Role in this project:
ML Engineer
ML EngineerContributions:13 commits, 4 PRs, 9 comments in 5 months
Contributions summary:Selim primarily contributed to the `dt2vw` function within the `r.vw` package, which transforms data.tables into the Vowpal Wabbit (VW) data format. Their work included defining the expected format for namespaces and adding the ability to handle datasets with more than 100 variables. Additionally, they modified the function to append data to existing files and added the functionality to handle the tag variable. This suggests a focus on data preparation and model input for a machine learning system.
hashingtechniquescpppythonactive-learning
selimrbd/py-obsidianmd
Aug 2022 - Dec 2022
Python interface to your Obsidian notes
Contributions:169 commits, 80 pushes, 2 branches in 4 months
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.