Assistant Professor at the Data and Artificial Intelligence Initiative, Faculty of Physical and Mathematical Sciences, University of Chile. I study how to make natural language AI more interpretable, fair, safe and aligned with human values and rationales. My research advances Trustworthy Natural Language Processing, with a focus on online harms and high-stakes applications for underrepresented communities in the Global South.

I hold a Ph.D. and an M.Sc. in Natural Language Processing, both in Computer Science and Computational Mathematics from the University of São Paulo During my doctoral studies, I was a visiting researcher at the University of Southern California, an invited speaker at the Leibniz Institute for the Social Sciences, and was recognized with the AI for Good award by Bocconi University.

I also actively contribute to the international artificial intelligence and natural language processing research community serving as a program committee member and area chair for venues as ACL, NeurIPS, IJCNN, AAAI. I have also co-organized the International AAAI Conference on Web and Social Media, Workshop on Online Abuse and Harms, Workshop on Language Model Interpretability, Safety and Alignment, Explainable Deep Neural Networks for Responsible AI, and shared tasks on hate speech [i] [ii].

I am keen to supervise PhD, MSc, and undergraduate students whose interests align with my research. Feel free to contact me to discuss potential topics of mutual interest.