Joan Acero Pousa is a Data Science Master’s student at the Universitat Politècnica de Catalunya (UPC), where he collaborates with the N3Cat research group. His research focuses on Graph Neural Networks (GNNs), with an emphasis on graph classification tasks. He works as an AI Engineer at Inkan, developing computer vision systems and adapting open-source large language models to domain-specific applications. His previous experience includes full-stack development and data science projects. Joan is the co-author of a paper accepted at ESANN 2025, where he proposes a multilayer SVM architecture that enhances scalability through kernel approximation and linear optimisation. He holds a Bachelor's degree in Informatics Engineering from UPC, specialising in Computing. During his undergraduate studies, he participated in the Erasmus+ program at TU Delft, where he took advanced AI courses, including Deep Reinforcement Learning and Machine Learning. As part of his Master’s, he also attended the Artificial Intelligence Global Engineering Summer Program at the South China University of Technology in Guangzhou, China.