I am an Artificial Intelligence and Natural Language Processing researcher with a focus on Language Model Interpretability and Fairness. I obtained a Ph.D. and an M.Sc. in Natural Language Processing, both in Computer Science and Computational Mathematics, from the University of São Paulo (USP), as well as a B.Sc. in Information Systems and a B.A. in Linguistics. During my Ph.D., I was a visiting researcher at the University of Southern California (USC) in the USA and an invited researcher and speaker at the Leibniz Institute for the Social Sciences (GESIS) in Germany. My work has received both national and international recognition, including the Google Latin America Research Award (LARA), the Maria Carolina Monard Award for the Best Thesis in Artificial Intelligence, and the Trevisan Prize for Students “AI for Good,” awarded by the Computer Science Department of Bocconi University and EDGE. I was also nominated by the Brazilian Computer Society (SBC) for national thesis awards in Computer Science and in Computational Social Science. I actively contribute to the international AI and NLP research community, serving as a program committee member and area chair for leading venues such as ACL, AAAI, IJCNN, and ACM. I have also co-organized workshops including the Workshop on Online Abuse and Harms (WOAH), and Explainable Deep Neural Networks for Responsible AI (DeepXplain), along with shared tasks on hate speech detection [i] [ii]. My research aims to enhance the interpretability and robustness of language models while ensuring alignment with safety, factuality, and fairness. With significant contributions to addressing hate speech and misinformation in underrepresented communities, my research advances human-centered artificial intelligence by developing rigorous computational methods and benchmark datasets that promote fairness, transparency, and accountability in NLP systems.