Stockholm — --:--

Mauro
Luzzatto

Machine Learning Engineer at Epidemic Sound, where I train, evaluate, and use latent diffusion models for audio. I focus on audio generation models that help creators customize music for their videos.

→ github.com/MauroLuzzatto → linkedin.com/in/mauro-luzzatto → mauro.luzzatto@gmail.com
01Now

Currently shipping Adapt, Epidemic Sound’s AI music editing tool

Role Machine Learning Engineer, Generative AI
Tenure At Epidemic Sound since Feb '22
Base Stockholm since 2021
From Switzerland

I work on Adapt, Epidemic Sound’s AI music editing tool. Day-to-day, that includes training latent diffusion transformers, building data infrastructure to train them at scale, and prompt engineering to get the most out of the models.

Before this, I joined Epidemic Sound as a Data Engineer, building the data platform and migrating event-tracking infrastructure to Snowplow.

Previously, I worked as a Data Scientist using NLP and machine learning at IBM in Zurich, and conducted research in legal NLP at ETH Zurich.

I studied Computer Science and Energy Science at ETH Zurich, with an exchange semester at KTH in Stockholm.

02Focus

Things I think about most days

A.

Generative AI for audio — and how to train, evaluate and scale the generative models.

Diffusion · Data · Evals
B.

ML infrastructure — data pipelines, training optimization, multi-GPU workflows.

Scale · GPU · Pipelines
C.

AI agents — building agentic workflows that connect generative models to real products.

Agents · ADK · Tooling
D.

Software craft — testing, docs, readable code, observability.

Engineering · Quality
03Selected Work

Open-source and side projects

01 / 03

explainy

Python scikit-learn SHAP GH Actions

A library for generating ML model explanations in Python — feature-importance for individual samples through a small, scikit-learn-flavored API. Four algorithms, global or local, contrastive or not.

→ Repo Docs Paper
02 / 03

Lyrics Translator

Hugging Face NLP Genius API

A Python module that pulls lyrics from Genius and runs them through Hugging Face translation models into the language of your choice. Handy for understanding what your favorite track is actually saying.

→ Repo Docs Demo
03 / 03

Entropy in Legal Language

word2vec Gensim NLP

A method for measuring word ambiguity in legal corpora using word2vec embeddings — applied to opinions of the U.S. Supreme Court and the German Bundesgerichtshof, comparing common-law and civil-law systems.

→ Repo
04Research

Papers, supervision, and slower work

2026 Epidemic Sound AI Research Blog: When music generation models get mixed signals — investigating conditioning conflicts in Adapt Epidemic Sound
2026 Supervising a KTH Master’s thesis — instruction-tuning a latent music diffusion model, extending SAO-Instruct to music. Ongoing. KTH
2025 explainy — a companion paper on generating explainable Machine Learning predictions in Python ACM
2021 Entropy in Legal Language — measuring entropy in U.S. Supreme Court and German Bundesgerichtshof opinions with word embeddings ETH
05Stack

Tools I reach for, most days

Machine Learning
Python PyTorch Hugging Face Diffusers scikit-learn spaCy
GenAI
Latent Diffusion (DiT) VAEs Google ADK Gemini API OpenAI API
MLOps & Infra
GCP AWS Dataflow / Beam Modal Docker Terraform GitHub Actions Weights & Biases
Data
BigQuery dbt Airflow Snowplow SQL
Web & Viz
FastAPI Streamlit Gradio Looker htmx TailwindCSS
Certifications
2023 Google Cloud Professional Data Engineer GCP
2021 AWS Solutions Architect — Associate AWS
2021 AWS Machine Learning — Specialty AWS
2019 Azure Architect Technologies (AZ-300) Azure