Summary

Research scientist role focused on generative audio, including vocal synthesis, music post-training alignment, and iterative audio editing. The role uses Python, PyTorch, NumPy, diffusion, and flow matching models, with remote flexibility across EMEA and collaboration during CET and EST core hours.

Responsibilities

• Conduct research in generative audio
• Develop diffusion and flow matching models
• Run large-scale experiments on Spotify infrastructure
• Create generative music product applications
• Collaborate with scientists and product teams
• Publish findings and present at conferences