Sonauto

At Sonauto we're building a platform for creating, sharing, and listening to music made by people with the help of our in-house generative music model Melodia. With Sonauto, people who have never made music before can have fun and express themselves in a completely new way.

We're working on the most fun application of the most bleeding edge research, what more is there to say?

Languages: Python (PyTorch), JavaScript (TypeScript)

We're training state of the art generative models in a completely new modality where the standard of quality is significantly higher than those that came before (hands with three fingers is fine in images, but miss a beat in a song and it's ruined). Accordingly, we are consistently implementing and inventing new generative architectures and improving current ones.

Right now we're doing distributed training at the scale of hundreds of H100s on diffusion models, GANs, language models, and more written in PyTorch.

However, we're not a pure research lab, our models go right into production and are generating tens of thousands of songs within days of (and frequently even before) finishing training. Our most important goal is the product itself, so extensive experience in JavaScript (our frontend is React/NextJS) and backend development are also important to us.