Research Scientist - Generative Audio

About the role

We are seeking Research Scientists to join our Artist-First AI Music Lab to pioneer and advance state-of-the-art generative technologies for music. You will invent new listening experiences that center and celebrate artists and creatives while leveraging our platform to reach millions of users. This role involves conducting groundbreaking research and collaborating with cross-functional teams to craft innovative solutions.

Responsibilities

• Conduct groundbreaking research in generative audio using diffusion or flow matching models
• Focus on research areas including vocal synthesis, post-training techniques, and audio editing
• Run large-scale experiments using extensive infrastructure and data
• Create practical applications that harness generative technologies
• Collaborate with scientists, engineers, product managers, designers, and researchers
• Engage with the broader research community by publishing findings and attending conferences

Required skills

• Generative modeling
• Machine learning
• Music information retrieval
• Speech processing
• Audio processing
• Signal processing
• Probabilistic modeling
• Python
• PyTorch
• NumPy

Nice to have

• Computer vision

Qualifications

• Ph.D. in Computer Science, Mathematics, Engineering, or a related field

About the Company

Spotify is a platform that connects more than 700 million monthly active users with music and audio content. We are committed to an artist-first approach, ensuring fair compensation and choice in participation for creators.