Background

About

I’m a Computer Science MSc student at Sapienza University, working across applied AI, data, and scientific computing.

This page is the background behind the projects: how I study, what I tend to build, and the tools I reach for when turning an idea into something testable.

See projects Contact
Based in Italy • Last updated: April 2026

Education

  • MSc Computer Science 2025–Present
    Sapienza University of Rome
  • Bachelor Degree in Applied Computer Science & Artificial Intelligence 2022–2025
    Sapienza University of Rome · 110 cum laude
  • Diploma di Liceo Scientifico 2017–2022
    Liceo Scientifico A. Romita · 100 e lode

Current direction

  • Applied AI: models that solve concrete tasks, expose their limits, and can be evaluated clearly.
  • Scientific data work: graph, vision, time-series, and bioinformatics problems.
  • Reliable experiments: readable notebooks, reproducible runs, and practical diagnostics.
  • Readable outputs: demos, notes, and summaries that make the reasoning behind a result easy to inspect.

Working style

Small experiments, clear evaluation

I like starting from the question and the data before choosing the model. The implementation matters because a good experiment should be easy to rerun, inspect, compare, and explain after the first result looks promising.

Reproducible runs Clean evaluation Visual diagnostics Small tools

Tools

Core toolkit

  • Python: NumPy, pandas, Matplotlib, scikit-learn, notebooks, data cleaning
  • Deep learning: PyTorch, PyTorch Lightning, PyTorch Geometric, model evaluation
  • Vision & graphs: OpenCV, torchvision, NetworkX, Gephi, post-processing
  • Engineering: Git, Docker when useful, HTML/CSS, JavaScript, OpenAPI, SQL
  • Workflow: reproducible runs, visual checks, compact documentation, small demos

Domains

Where I apply it

  • Bioinformatics: interactomes, protein interaction prediction, enrichment workflows, correlation analysis
  • Computer vision: anomaly detection, localization, masks, boxes, synthetic data
  • Dynamical systems: forecasting, recursive prediction, reinforcement learning, chaotic systems, stability checks
  • Research prototypes: small web/API tools, demos, and visual summaries