Engineer, musician, and curious mind. Hi, I’m Fernando!
I’m an engineer and researcher working on machine learning and signal processing for music and audio applications. My interests range across generative models, music information retrieval, and real-time audio software, with a focus on building practical tools for musicians and technologists.
I’m completing an MSc in Sound and Music Computing at the Music Technology Group (MTG), Universitat Pompeu Fabra in Barcelona, following a BSc in Electronics Engineering specializing in Acoustics from Instituto Politécnico Nacional in Mexico City. I started out as a software and data engineer in consultancy before moving into audio and music research.
Some highlights from my journey:
- Sony CSL Paris: Research Scientist Intern (2026), working on machine learning and signal processing for music and audio applications.
- Research: two papers accepted at ISMIR 2026, quantifying how much of a hybrid music mixture is AI-generated (first author), and assessing AI-music detection in real broadcast monitoring.
- BMAT Music Innovators: R&D Engineer Intern, research & model development for AI-generated music detection in real broadcast monitoring scenarios, in collaboration with MTG.
- Dolby Laboratories: Software Engineering Intern, contributed to C++ audio libraries, DSP pipelines, and prototyped ML-driven sound analysis tools.
- Audio Developer: at Ear Candy Technologies and MTG, built audio plug‑ins with the JUCE Framework and led essentia‑plugins, a real-time audio analysis toolkit.
- Data Engineering: designed ETL processes, databases, APIs, and deployed ML models into production.
- Community: speaker at Audio Developer Conference 2024, Rock-Solid Releases on CI/CD for audio developers. Contributor to several initiatives from The Sound of AI with Valerio Velardo.
Check out my portfolio and publications, and feel free to reach out! 😁