About
I am an AI Researcher at Intesa Sanpaolo, working on industrial research projects on LLMs for CV evaluation and fairness, and on GenAI for music generation that is copyright- and GDPR-compliant. I joined the group in January 2026 following the acquisition of CENTAI, where I had been an AI researcher since October 2023.
I hold a PhD in Computer Science from Graz University of Technology, completed in June 2026 under the supervision of Prof. Dr. Fariba Karimi with a thesis titled “Statistical and Structural Approaches to Algorithmic Fairness”, graded Sehr gut (1), the highest grade on the Austrian scale.
My background is in mathematics: I obtained my Bachelor's degree at the University of Florence and a Master's in Stochastics and Data Science at the University of Turin (110/110 cum Laude). My research interests center on LLM alignment, algorithmic fairness and responsible AI, building on a background in ranking, recommender systems and network science: in particular, how ranking and recommendation algorithms shape visibility and connections between groups of users, and the impact this has on society.
Experience
AI Researcher — Intesa Sanpaolo
01/2026 – Present
Industrial research projects:
- LLMs for CV evaluation and fairness.
- GenAI for music generation, copyright- and GDPR-compliant.
AI Researcher — CENTAI (acquired by Intesa Sanpaolo)
10/2023 – 01/2026
Research on bias and fairness in ranking methods and recommender systems. Industrial and European research projects:
- Prototype for churn prediction of isybank customers based on recurrent neural networks.
- Clustering pipeline for financial assets in the context of prudent valuation.
- European project: fairness assessment pipeline for AI models predicting side effects of breast-cancer radiotherapy.
Early Stage Researcher — GESIS, Leibniz Institute for the Social Sciences
10/2020 – 09/2023
Researcher in the Department of Computational Social Sciences, working on network-based recommendation algorithms and fair ranking algorithms.
Research Internship — Eurecat, Technology Centre of Catalonia
01/2023 – 05/2023
Developed a method to tackle group bias from human relevance feedback in rankings.
Traineeship — European Central Bank
05/2020 – 09/2020
Department of Statistics. Monitoring of a large-scale Credit Risk Parameters database, plus development of a machine-learning model to detect outliers in crypto-asset trading platforms.
Research Internship — ISI Foundation, Institute for Scientific Interchange
09/2019 – 04/2020
Research project on theoretical and practical connections between Graph Neural Networks and Spatial Statistics.
Education
PhD in Computer Science — Graz University of Technology
10/2020 – 06/2026, Austria
Final grade: Sehr gut (1), the highest grade on the Austrian scale.
Supervisor: Prof. Dr. Fariba Karimi.
Thesis: Statistical and Structural Approaches to Algorithmic Fairness.
Started at RWTH Aachen University and transferred to TU Graz following my supervisor.
NoBIAS — Artificial Intelligence without Bias (Marie Skłodowska-Curie ITN)
10/2020 – 09/2023
European Union's Horizon 2020 research and innovation programme. NoBIAS investigates approaches for creating AI-driven decision-making systems free from biases, training a cohort of 15 researchers including myself.
Master's degree in Stochastics and Data Science — University of Turin
09/2017 – 04/2020, Turin, Italy
Final grade 110/110 cum Laude.
Thesis: Thinking in Space: a Comparison between Spatial Statistics and Graph Neural Networks.
Erasmus+ — Johannes Kepler University
09/2018 – 07/2019, Linz, Austria
Master's courses in Machine Learning, Deep Learning, Time Series, Bayesian Statistics and Data Science.
Bachelor's degree in Mathematics — University of Florence
09/2013 – 10/2017, Florence, Italy
Final grade 110/110.
Thesis: Cryptographic Applications of the LLL Algorithm.
Research
Selected publications
- Ferrara, A., Cozzi, F., Perotti, A., Panisson, A., & Bonchi, F. (2025). Size-adaptive Hypothesis Testing for Fairness. Advances in Neural Information Processing Systems (NeurIPS 2025).
- Ferrara, A., García-Soriano, D., & Bonchi, F. (2025). Beyond Shortest Paths: Node Fairness in Route Recommendation. Proceedings of the VLDB Endowment, 18(9), 3230–3242.
- Ferrara, A., Bonchi, F., Fabbri, F., Karimi, F., & Wagner, C. (2024). Bias-aware Ranking from Pairwise Comparisons. Data Mining and Knowledge Discovery, 38(4), 2062–2086.
- Ferrara, A., Espín-Noboa, L., Karimi, F., & Wagner, C. (2022). Link Recommendations: Their Impact on Network Structure and Minorities. In 14th ACM Web Science Conference 2022, pp. 228–238.
Full list: Google Scholar.
Reviewer & Program Committee
- Reviewer: NeurIPS (2024, 2025), ICLR (2025), KDD (2025), ICML (2025), ACL (2025), EWAF (2024), ACM TSC (2023), WWW (2022), ACM HT (2021).
- Program Committee: AAAI (2025).
Honours & Awards
- Deutsche Forschungsgemeinschaft (DFG) — Project no. 530081187, €220K, University of Mannheim. User and data bias in people-ranking systems. Awarded a 3-year grant; declined to join CENTAI.
Skills
Quantitative & data analysis
- Deep learning — GNNs, CNNs, LSTMs, auto-encoders.
- Large language models — fine-tuning, evaluation, alignment.
- Fairness and explainability techniques.
- Learning to rank and recommender systems.
- Time series analysis and forecasting.
- Network analysis.
- Bayesian statistics.
Programming & tools
- Python — 8 years.
- Git, shell scripting and Unix — 5 years.
- R — 3 years.
- C, Matlab — 1 year.
Languages
- Italian — mother tongue.
- English — C2 (full professional proficiency).
- Spanish — B2.
- German — A2.
Contact
Feel free to reach out about research collaborations, talks or anything else.
- name.surname1992@outlook.it
- Florence, Italy