Audio ML Research Scientist

Suno is hiring a Senior Audio ML Research Scientist to work on our music generation models. You will develop novel architectures for creating high-fidelity, musically coherent audio that captures the nuances of different genres, instruments, and styles. This is a research-heavy role where you will explore new approaches to audio tokenization, temporal modeling, and controllable generation. Your work will enable millions of people to create music with AI. The ideal candidate has deep expertise in audio ML, generative models, and a passion for music and creativity.

- 5+ years of audio/music ML research experience - Experience with audio generation models - Strong PyTorch and distributed training skills - Published research in audio ML venues (ISMIR, ICASSP, etc.) - Understanding of music theory is a strong plus - PhD in Audio/Music ML or related field