Milan, Italy ✱AI Engineer Intern
I teach machines to act in commerce, see bodies heal, and read symptoms.
01 — Selected work
Post-stroke rehabilitation from a smartphone camera. OpenCV movement recognition plus a custom PyTorch model that gives patients real-time exercise feedback from visual data alone.
NLP classifier predicting 22 medical diagnoses from patient symptom descriptions (GretelAI dataset, 1,065 samples). Fine-tuned transformer models: BERT/ClinicalBERT (97% acc, F1=0.97) and Flan-T5 (94% acc), outperforming classical baselines.
Regression models to predict bike sharing demand from weather, time, and calendar features. Implemented preprocessing (scaling, one-hot encoding, PCA/LDA) and trained models including Linear/Ridge/Lasso/ElasticNet, Random Forest, and XGBoost.
02 — Experience
Stealth AI startup
Frontier agentic work at a stealth AI startup in agentic commerce: building systems that let AI agents read, compare, and act in real catalogs.
Reviva
Co-led the ML and computer-vision pipeline for an AI-powered post-stroke rehabilitation app: patient movement recognition from smartphone camera data, with real-time exercise feedback from visual input alone.
03 — Recognition
3rd
of 0
EIT Health i-Days
Madrid — 2025
Reviva, post-stroke rehabilitation with real-time camera feedback.
Winner
Biomedicine & AI
Bologna StartUpDays
Bologna — 2025
Winner. Delivered a working real-time prototype.
3rd
of 0
EIT Health i-Days
Italy — 2024
Represented Italy at the European Finals.
Also: Machine Learning Specialization (Andrew Ng, 2024) · Advanced Python for Data Science (University of Pavia, 2023)
Hiring for ML? Get in touch →
04 — About
Right now: frontier agentic work in commerce. Before that: computer vision that watches stroke patients recover, transformers that sort symptoms into 22 diagnoses, ensembles that forecast bike demand. Three international juries put the healthcare work on podiums. The spec sheet has the rest.