Flavio Schneider
Machine Learning Researcher at ElevenLabs
Lugano, Ticino, Switzerland
Summary
🤩
Rockstar🎓
Top SchoolFlavio Schneider is a machine learning researcher with 11 years of engineering experience, currently advancing generative audio and voice technologies at ElevenLabs. Trained at ETH Zürich (BSc Computer Science, MSc Machine Intelligence), he blends strong CS fundamentals with hands-on ML engineering—evidenced by contributions to audio diffusion models in PyTorch, UNet refinements, learned time embeddings, and custom noise schedulers. Based in Lugano, Switzerland, he pairs Android, web development and design sensibilities with research-driven experimentation to move prototypes toward production. Practical and methodical, he brings both academic rigor and production-focused implementation skills to challenging generative audio problems, and he’s active in the open-source community through projects like archinetai/audio-diffusion-pytorch.
11 years of coding experience
SAMT InformaticaBachelor's degree, Computer Science, Bachelor's degree, Computer Science at ETH ZürichSwiss Federal Matura Passerelle, Swiss Federal Matura Passerelle at Liceo Cantonale di Locarno
Italian, English, German, French
Github Skills (9)
enet10
pytorch10
machine-learning10
deep-learning10
python8
data-structure7
data-structures7
algorithm7
algorithms7
Programming languages (7)
Github contributions (5)
archinetai/audio-diffusion-pytorch
Jul 2022 - Jan 2023
Audio generation using diffusion models, in PyTorch.
Role in this project:
ML Engineer
ML EngineerContributions:100 releases, 187 commits, 5 PRs in 6 months
Contributions summary:Flavio primarily focused on implementing and refactoring the core components of the audio diffusion model. Their contributions include adding diffusion-related functionality, refining the UNet architecture, and updating the loss function. They also integrated a learned time embedding for improved performance and implemented a new noise schedule sampler, demonstrating a strong understanding of diffusion model architectures and training techniques for audio generation.
pytorchdeep-learningaudiodiffusiondiffusion-models
archinetai/a-unet
Dec 2022 - Feb 2023
A toolbox that provides hackable building blocks for generic 1D/2D/3D UNets, in PyTorch.
Contributions:16 releases, 31 commits, 1 PR in 1 month
pytorchbuilding-blocksdeep-learningtoolboxcomputer-vision
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.