I am currently a predoctoral student at Universidad de Zaragoza (Spain), under the supervision of Jorge Gracia and José Luis Mendívil. My work is funded by a grant from the Government of Aragón (DGA).

My PhD project revolves around large language models (LLMs), specifically to see if they come to encode grammatical knowledge as we humans do and see if we can leverage that knowledge to adapt them to low-resourced and endangered languages, those that do not have billions of documents to train a model from scratch! I am also a member of SID (Spanish acronym for "Distributed Information Systems"), a research group at Universidad de Zaragoza.

I studied Spanish studies in Universidad de Zaragoza (2016-2020), and then pursued a master's degree in Universidad del País Vasco in 2022 on Computational Linguistics (Máster en Análisis y Procesamiento del Lenguaje). Although my original studies are on the Humanities, I love computer science ever since I was a kid and I have been tinkering with old computers and vintage software ever since I have reasoning.

I have done an internship at Elhuyar in 2022, an NLP-oriented institution in the Basque Country, in a project supported by the Linguistics Department of the Government of Aragón (Spain), to create an (unreleased) ASR system for Aragonese, a low-resourced language. From 2022 to 2023 I worked alongside Fernando Domínguez-Castro and Borja Latorre to create an automatic system for the detection of drought impacts in newspaper articles, and its integration in automatized records, using NLP tools.