Research Scientist - Generative Audio

About the role

We are seeking Research Scientists (all seniority levels) to join our Artist‑First AI Music Lab, pioneering state‑of‑the‑art generative technologies for music that create breakthrough experiences for fans and artists. The lab’s four guiding principles are partnerships with record labels, distributors and music publishers; choice in participation for artists and rightsholders; fair compensation and new revenue streams; and deepening artist‑fan connections through AI tools.

Responsibilities

• Conduct groundbreaking research in generative audio using diffusion or flow‑matching models, focusing on vocal synthesis, post‑training techniques, or iterative music editing.
• Run large‑scale experiments leveraging Spotify’s infrastructure and its 700 million‑plus monthly active users.
• Create practical applications that push the boundaries of listening experiences.
• Collaborate with scientists, engineers, product managers, designers, user researchers, and analysts to craft innovative solutions.
• Influence Spotify’s products, tools, and services across the organization.
• Engage with the broader research community by publishing findings, delivering talks, and attending top conferences.

Requirements

• Ph.D. in Computer Science, Mathematics, Engineering, or a related field (industry experience is a plus).
• Experience in one or more of: generative modeling, machine learning, music information retrieval, speech/audio processing, signal processing, probabilistic modeling, computer vision, or related areas.
• Deep expertise in at least one focus area: vocal/speech synthesis, post‑training alignment techniques (e.g., PPO, GRPO, DPO), or audio‑to‑audio generation and text‑guided music editing.
• Publications at leading conferences such as ICASSP, ISMIR, INTERSPEECH, ICLR, AAAI, IJCAI, NeurIPS, ICML, CVPR, ECCV, ICCV, or similar venues.
• Strong coding skills in Python, PyTorch, and NumPy.
• Creative problem‑solving mindset, passion for building products that add real value to millions of users.
• Enthusiasm for turning research ideas into scalable products.
• Ability to explain complex topics simply and build strong relationships with colleagues and stakeholders.

Location

Flexible work location within the North Americas region; the team operates in the Eastern Standard Time zone for collaboration.

Schedule

Core working hours: CET 3 pm – 6 pm / EST 9 am – 12 pm.

Pay

United States base range: $133,194 – $190,278 plus equity.

Benefits

• Health insurance
• Six‑month paid parental leave
• 401(k) retirement plan
• Monthly meal allowance
• 23 paid days off
• 13 paid flexible holidays