Research Scientist - Generative Audio

Spotify’s Artist-First AI Music Lab seeks research scientists across seniority levels. Work develops diffusion and flow-matching methods for vocal synthesis, preference-aligned music generation, and audio editing, then tests and translates research into products with interdisciplinary teams. The role includes publication and scientific presentations. This permanent role is listed in New York and permits remote work within North America where Spotify has a work location.

Collaboration follows the team’s Eastern-time schedule. The advertised US base salary is USD 133,194–190,278 plus equity. The application form is open and no fixed closing date is stated.

PhD in computer science, mathematics, engineering or a related field; expertise in generative/audio modeling, synthesis, post-training alignment or music editing; relevant research publications; strong Python, PyTorch and NumPy skills.