I am a Ph.D student at Nexa Center for Internet and Society, a research center of the Department of Control and Computer Engineering of the Politecnico di Torino.

I am working with Professors Juan Carlos De Martin and Antonio Vetrò.

My research focuses on data fairness in the field of Responsible AI / AI Safety, with the overarching goal of investigating and addressing algorithmic discrimination in real-world systems. I study how data quality, data documentation and data ethics intersect to enable or prevent unfair outcomes in AI applications.

I approach these challenges through empirical methods, conducting algorithmic audits and black-box testing of deployed systems across various domains, from automated decision-making systems to large language models. My work combines quantitative analysis of bias and fairness with the development of practical frameworks for measuring, documenting and improving datasets.

A central thread in my research is understanding how inadequate data practices (from poor documentation to imbalanced representation) can lead to discriminatory outcomes, particularly against marginalized and vulnerable groups. I investigate these issues both by testing existing systems and by developing tools that help practitioners build more accountable and equitable data-driven software.