cv

Visiting Researcher

School of Informatics, University of Edinburgh

Teaching Assistant

University of Trieste

Teaching assistant for the Master's course in Probabilistic Machine Learning held by Luca Bortolussi.

• Lecturing
• Correcting and writing course notes
• Preparing laboratories and exercitations
• Preparing and correcting homeworks

PhD Student

University of Trieste

PhD candidate in Applied Data Science & Artificial Intelligence. Research topic on generative models for tabular data generation. Reviewer at AAAI26 conference.

Research Scientist

Aindo SpA

Researcher on generative models for synthetic data generation.

R&D Scientist

Trality GmbH

Research and engineering for quantitative finance. Time series modeling (cryptocurrencies), ML pipeline development, reinforcement learning research, trading strategies optimization, implementation of statistical indicators and optimizers into production code, back-end development.

IT Analyst

Deloitte Consulting

Statistical analysis on datasets in the banking field, definition and implementation of automatic data quality controls, data governance solutions analysis in the banking field.

Machine learning developer intern

Aindo SpA

Development of a deep learning model able to generate multivariate financial time series simulating real dynamics and statistical properties..

Tutor

Casa dello Studente

Tutor in math, physics and computer science.

PhD

University of Trieste

Applied Data Science & Artificial Intelligence

Master of Science

University of Trieste, SISSA, ICTP

Data Science & Scientific Computing

• Advanced Programming and Algorithmic Design
• Numerical Analysis
• Probabilistic Machine Learning
• Foundations of High Performance Computing
• Stochastic Modelling and Simulation

Bachelor of Science

University of Brescia

Computer Science and Engineering

Excellence Scolarship for DSSC Students

SISSA (International School for Advanced Studies)

The scholarship was awarded to 4 incoming students in the department. It covered housing expenses and provided a monthly stipend for the whole duration of the Master's Degree.

Graph-Conditional Flow Matching for Relational Data Generation

AAAI

We propose a generative model for relational data that generates the content of a relational dataset given the graph formed by the foreign-key relationships by learning a deep generative model of the content of the whole relational database by flow matching.

Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints

AAAI

We develop a method that, given a pre-trained unconditional score-based generative model, samples from the conditional distribution under arbitrary logical constraints, without requiring additional training, and is designed for approximating the true conditional distribution.

Multi-Objective reward generalization: Improving performance of Deep Reinforcement Learning for selected applications in stock and cryptocurrency trading

Neural Computing & Applications

We verify the reward generalization property of the proposed Multi-Objective algorithm on stock and cryptocurrency trading, and provides preliminary statistical evidence showing increased predictive stability over the corresponding Single-Objectives strategy.