Who I Am
I'm a Senior AI Engineer at Mediapro, building generative-AI and computer-vision systems for live sport and broadcast — bringing cutting-edge research into production.
My work spans generative AI, deep learning, 3D reconstruction, and large language models. I hold a PhD from the University of the Basque Country, where I researched collaborative, multi-user augmented reality experiences for education (defense slides).
I have worked in Italy, Germany, and Spain at both research institutions and software companies, from start-ups to large consulting firms. Along the way I picked up four foreign languages and a good number of programming ones too.
Outside of work, I spend my free time with friends and family, playing basketball, reading, travelling, and discovering Gipuzkoa by bicycle. I also try to learn something new every day, and I'm especially fond of the web as a wonderful interactive medium for discovery and understanding.
I don't have the time or the consistency to keep a blog, but I do maintain a now page with what I'm currently up to.
Expertise
Technologies and domains I work with daily.
Things I’ve Built
A random selection of my work, from brand analytics and Gaussian-splat 3D reconstruction in live sport to collaborative AR research. Refresh the page to shuffle the set.
Research into NeRFs and 3D Gaussian Splatting as a pipeline for capturing real-world locations as photorealistic assets for LED-volume virtual production. Evaluated camera setups, algorithms (nerfacto, splatfacto, MCMC), and Unreal Engine integration — benchmarked against RealityCapture and Postshot. The work produced a desktop application that runs COLMAP pose estimation followed by user-chosen reconstruction either locally or on Azure, with a browser-based Gaussian splat viewer.
A computer-vision system that measures how much screen time each brand gets in football broadcasts. A YOLO detector finds the perimeter boards and LED signage; a DenseNet201 classifier sorts each into one of 52 brands — coping with small, motion-blurred crops, a 40× class imbalance, and LED ads that rotate weekly. Runs in production on Azure, validated against human annotators.
ARoundTheWorld is a multiplatform collaborative AR geography application built on the cleAR architecture. It was evaluated with 44 students across three schools and represents the final paper of my PhD, validating that the architecture can produce applications that integrate seamlessly into existing school curricula.
Selected Work
During my years as a researcher, I published more than 30 articles, the majority of them open access. The papers below highlight the core of my PhD work; the full list lives on the publications page, or you can visit my Google Scholar profile.
Get in Touch
Whether you want to collaborate on a research project, discuss AI, or simply say hello; I'm always happy to connect.