Marco Di Giovanni
Senior Data Scientist
Milan, Lombardy, Italy
Summary
👤
Senior🎓
Top SchoolMarco Di Giovanni is a Senior Data Scientist based in Milan with nine years of experience bridging academic research and product-focused ML engineering, currently applying pre-trained language models to social media and commercial problems at Foolfarm. He holds a PhD and postdoctoral experience from Politecnico di Milano and research stints at Harvard IACS, where he explored neural methods for differential equations and contributed to the NeuroDiffEq open-source library. Marco has taught and supervised multiple master theses on multilingual semantic similarity and vaccine-related stance detection, and co-leads the VaccinItaly project monitoring Italian COVID-19 conversations. As an active open-source contributor, he improved natural language transformations in the widely used NL-Augmenter repository, adding practical augmentations and maintainability enhancements. Outside work he balances rigorous quantitative work with creative pursuits—he plays piano and ukulele—and brings that same blend of precision and curiosity to ML research-for-impact.
9 years of coding experience
1 year of employment as a software developer
Scuola Internazionale Superiore di Studi Avanzati di TriesteMaster of Science (M.Sc.), Physics of Complex Systems, 110/110 cum Laude, Master of Science (M.Sc.), Physics of Complex Systems, 110/110 cum Laude at Politecnico di TorinoInternational Centre for Theoretical PhysicsUniversity of BolognaHigh School Scientific Diploma, Liceo Scientifico P.N.I., 100/100, High School Scientific Diploma, Liceo Scientifico P.N.I., 100/100 at Liceo A. Volta - RiccioneUniversité Paris DiderotUniversité Pierre et Marie CurieUniversité Paris-Sud
Italian, English
Github Skills (9)
rule-based10
nlp10
python10
natural-language-processing10
rule-engine10
data-augmentation9
text-manipulation9
json9
machine-learning8
Programming languages (1)
Github contributions (5)
GEM-benchmark/NL-Augmenter
Aug 2021 - Sep 2021
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations
Role in this project:
ML Engineer
ML EngineerContributions:27 reviews, 20 commits, 7 PRs in 1 month
Contributions summary:Marco's contributions focused on implementing and improving natural language transformations within the NL-Augmenter project. Their work involved adding new transformations, such as an underscore trick and unit conversion, and integrating them into the existing framework. The user also added keyword tags and made code enhancements, improving the project's functionality and maintainability. Additionally, separate JSON files were created and integrated for dictionary data.
nlpinformation-theorysentencedeep-learningmachine-learning
marco-digio/NL-Augmenter
Jul 2021 - Sep 2021
NL-Augmenter 🦎 → 🐍 A Collaborative Repository of Natural Language Transformations
Contributions:28 pushes, 9 branches in 2 months
nlpdeep-learningentity-linkingmachine-learningnatural-language
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.