Tommaso Carraro
Research Intern at Disney Research
Padua, Veneto, Switzerland
Summary
👤
Senior🎓
Top SchoolTommaso Carraro is a research-focused software engineer with 8 years of experience, currently developing LLM-powered recommendation systems at Disney Research Zurich. He holds a PhD in AI from the University of Padova with a visiting research stint at Rutgers, and has a strong track record building LLM agents and Neuro-Symbolic recommenders during multiple internships at SonyAI, including a RecSys 2025 paper and a production-oriented proof-of-concept for the SonyLIV platform. He combines deep academic expertise in NeSy integration with hands-on engineering in function-calling LLM architectures, vector stores, and recommender frameworks like RecBole and Qdrant. Notably, he demonstrated practical gains by improving small-model function-calling via in-context example retrieval and designed LLM reranking based on generated user personas. Based in Vigonza, Italy, he bridges research and productization, focusing on scalable, tool-enabled agents that make recommendations interpretable and interactive.
8 years of coding experience
1 year of employment as a software developer
Doctor of Philosophy - PhD, Brain, Mind and Computer Science, Doctor of Philosophy - PhD, Brain, Mind and Computer Science at Università degli Studi di PadovaHigh School Diploma, Computer Science, High School Diploma, Computer Science at ITIS Francesco SeveriMaster's degree, Computer Science, Master's degree, Computer Science at University of HelsinkiDoctor of Philosophy - PhD, Artificial Intelligence, Doctor of Philosophy - PhD, Artificial Intelligence at Rutgers University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (41)
fuzzy-logic10
neural-symbolic10
pytorch9
captcha-solver9
machine-learning9
keras9
hcaptcha9
hyperparameter-tuning8
recaptcha8
python8
deep-learning8
data-versioning8
tensorflow8
captcha-solving8
data-science8
Programming languages (3)
Github contributions (5)
tommasocarraro/LTNtorch
Nov 2021 - Sep 2025
PyTorch implementation of Logic Tensor Networks, a Neural-Symbolic framework.
Contributions:4 releases, 94 pushes, 4 branches in 3 years 10 months
neural-symbolicpytorchtensorneural-symbolic-computingfuzzy-logic
MisterWeeMan/MILCTdev
Dec 2017 - Mar 2018
Contributions:11 PRs, 139 pushes, 7 branches in 2 months
javascriptingegneria-del-softwareannodeldell
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.