Research Scientist, Generative Audio & Vocal Synthesis

Spotify; Greater London; On-site; GBP 70,000 - 120,000; Full time

Job summary

Spotify is seeking Research Scientists across all seniority levels to join our Artist-First AI Music Lab. We pursue state-of-the-art generative audio technologies to create breakthrough listening experiences that put artists and creatives first.

You will conduct groundbreaking research in diffusion or flow matching models for vocal synthesis, post-training alignment, and interactive editing. Collaborate with cross-functional teams and publish your findings to advance Spotify's products.

Qualifications

• PhD in Computer Science, Mathematics, Engineering, or a related field.
• Publications at leading conferences or journals are valued.
• Strong coding skills in Python, PyTorch and NumPy.

Responsibilities

• Conduct groundbreaking research in generative audio using diffusion or flow matching models.
• Collaborate with scientists, engineers, product managers, designers, user researchers, and analysts to craft innovative solutions.
• Publish findings and engage with the broader research community.
• Run large-scale experiments leveraging Spotify's infrastructure and data.
• Contribute to building products that scale to millions of users.

Skills

Python

PyTorch

NumPy

Education

PhD in Computer Science, Mathematics, or Engineering

Job description

Spotify is seeking Research Scientists across all seniority levels to join our Artist-First AI Music Lab. We pursue state-of-the-art generative audio technologies to create breakthrough listening experiences that put artists and creatives first.

You will conduct groundbreaking research in diffusion or flow matching models for vocal synthesis, post-training alignment, and interactive editing. Collaborate with cross-functional teams and publish your findings to advance Spotify's products.