Luca Foppiano
Founder AI Engineer Text Mining at ScienciaLAB
Aveiro, Portugal
Summary
🤩
Rockstar🎓
Top SchoolLuca Foppiano is a Text and Data Mining engineer and founder with 12 years of experience building ML-driven document and knowledge extraction systems across research institutes, public organizations, and startups. He has led production integrations of Grobid at scale for the European Patent Office, contributed back-end improvements to the popular Grobid project, and architected large patent and scientific text pipelines using document databases and RAG approaches. His recent work spans LLM evaluation and fine-tuning for materials informatics, automatic construction of materials-property databases, and practical deployments of TDM in both research and industry settings. Comfortable bridging research and engineering, he has delivered seminars and taught TDM/ML topics while running R&D projects at Inria and the National Institute for Materials Science. Based in Aveiro, Portugal, he blends deep academic training (PhD-level work) with hands-on engineering—an unusual mix that fuels both reproducible research and production-ready tooling. Outside core development, he has a history of open-source experimentation (e.g., Grobid contributions) and a pattern of turning research prototypes into scalable systems.
12 years of coding experience
16 years of employment as a software developer
Vienna University of TechnologyMaster Computer Engineering, Master Computer Engineering at Università di PaviaDoctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at University of Tsukuba Communication General, Communication General at Toastmaster International
English, Italian, Spanish, French, Catalan, Japanese, Portuguese
Stackoverflow
157reputation
17kreached
10answers
8questions
Github Skills (16)
javas10
java10
modeling9
trainings9
machine-learning9
develop9
nlp9
windows6
grobid6
return-value6
pymupdf6
bash6
pdfplumber6
netbeans6
jvm6
Programming languages (13)
Github contributions (5)
kermitt2/grobid
Feb 2016 - Dec 2022
A machine learning software for extracting information from scholarly documents
Role in this project:
Back-end Developer
Back-end DeveloperContributions:4 releases, 36 reviews, 687 commits in 6 years 10 months
Contributions summary:Luca contributed to the Grobid project by adding UNIT model names, tagging libraries, and creating a model directory if it doesn't exist during trainer execution. They modified the core Java files, including the GrobidModels and TaggingLabel, indicating work related to model definition and annotation. Further contributions include improving feedback for backend errors by adding error codes for specific failures.
pdfdeep-learningfulltextmachine-learningscientific-articles
lfoppiano/deep-learning-tutorials
Feb 2019 - Aug 2019
Tutorials, courses, solved exercises and examples of Deep Learning
Contributions:61 commits, 2 PRs, 55 pushes in 5 months
pythondeep-learningmachine-learningsolvedtensorflow
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.