Fernando Garcia de la Cruz

Barcelona, Spain | fergarciadlc@gmail.com

🌐 fergarciadlc.github.io | 🐙 GitHub | 💼 LinkedIn

Work Experience

Dolby Laboratories
Software Developer - Entertainment Tech | Internship
March 2025 – August 2025

General C++ software engineering
C and C++ libraries for audio and signal processing for internal use
Audio Plugins development
Internal research projects using AI models
Volunteering

Music Technology Group - UPF
Research Assistant - Audio Developer | Internship
May 2025 – Present

Integrated Essentia library in audio plugins for real-time processing using the JUCE framework
Developed essentia-plugins repository
Created multiple audio analysis plugins with CMake and Projucer build systems

Ear Candy Technologies
Audio Developer – DSP Engineer
August 2022 – March 2025

Globant
Python-Data Engineer – Data & Artificial Intelligence Studio
September 2021 – September 2024

Everis
Python Engineer – Data & Analytics
January 2021 – September 2021

Education

MSc Sound and Music Computing
Universitat Pompeu Fabra, Music Technology Group
September 2024 – 2026
Barcelona, Spain

BS in Electronics and Communications Engineering
Instituto Politécnico Nacional (ESIME)
Speciality in Acoustics
January 2015 – November 2019
Mexico City, Mexico

Publications

From Words to Sound: Neural Audio Synthesis of Guitar Sounds with Timbral Descriptors
September 2022
The Sound of AI Community (3rd author)
Presented at the 3rd Conference on AI Music Creativity (AIMC 2022)
DOI: 10.5281/zenodo.7088416

Selected Projects

Personal Open Source projects can be found in my GitHub and portfolio.

Essentia Plugins | May 2025 – September 2025
Developed essentia-plugins, a set of audio plugins using the Essentia library and the JUCE Framework.

The Sound of AI Community Projects | July 2022 – July 2023
Multiple roles in The Sound of AI community initiatives including: Assistant Director for the first Accelerator program (startup program in music-audio-AI), organizer and participant in the 1st Hackathon where I developed Modelizer (real-time audio processing VST), and contributor to the Open Source Research project with 200+ community members, co-authoring the published neural synthesis research.

Selected Open Source Projects (Music Technology): Orbit, Harmonic Playlist, Mictlan, Amaranth, gentone, FFT-conv-decv.

Conferences and Talks

🎤 Speaker: Audio Developer Conference 2024 | November, Bristol, UK
Talk: “Rock-Solid Releases” about CI/CD for Audio Plugins
🎥 Watch on YouTube

Socios Formadores (ITESM) | August 2023
Participated with Ear Candy Technologies in workshops on JUCE for the program “Socios Formadores” at Tecnológico de Monterrey (campus Mexico City and Puebla).

Expoacustica 2023 (IPN) | May 2023
Presented a workshop and a conference on Audio Plugins with Ear Candy Technologies at IPN’s Expoacustica 2023.

Mexsynthco 2023 | September 2023
Presented Amaranth (an open-source synth) with Ear Candy Technologies.

Ear Candy Meetings 2022
Delivered a talk on using the Spotify API to generate style- and key-based playlists from a reference song: video link.

Additional Experience

Teacher Assistant | 2025 - present
MTG-UPF - Barcelona
Generative Music AI workshop.

Ciencia desde Cero | August 2017 – January 2023
Scientific Communicator

Guit-Art Music School | November 2013 – June 2019
Guitar Teacher and Audio Engineer

Technical Skills

Category	Technologies & Tools
Audio/DSP Development	JUCE (C++), Essentia, Pure Data, Matlab
Programming Languages	Python, C/C++, Go, CMajor, Matlab
Machine Learning	scikit-learn, TensorFlow, Keras, Librosa
Data Engineering	Apache Beam, Airflow, Kafka, Spark (PySpark)
Data Analysis	NumPy, Pandas, SciPy, OpenCV
Data Visualization	Matplotlib, Seaborn, Plotly, Cufflinks
Cloud & DevOps	GCP, Docker, Travis CI, Jenkins, Kubernetes
Databases	SQL (Postgres, MySQL, BigQuery), NoSQL (MongoDB)
Web & API	HTML, CSS, JavaScript, Flask, Django, FastAPI
AI Tools	ChatGPT, DALL-E, Midjourney, Stable Diffusion

Languages

English (Fluent - Professional Proficiency)
Spanish (Native)