Research Scientist - Generative Audio

📋 Description

• Run large-scale experiments on diffusion-based audio at scale.
• Create practical applications using generative tech for listening experiences.
• Collaborate with scientists, engineers, PMs, designers, and researchers.
• Impact Spotify's products, tools, and services.
• Publish findings and present at conferences.

🎯 Requirements

• PhD in CS/Math/Engineering or related field; industry exp helpful.
• Deep expertise in generative modeling, ML, music information retrieval, or audio processing.
• Deep expertise in vocal/speech synthesis, or post-training alignment.
• Publications at ICASSP/ISMIR/INTERSPEECH, NeurIPS, ICML, CVPR, etc.
• Strong coding in Python, PyTorch, and NumPy.
• Creative problem solver, excited to turn research ideas into scalable products.

🎁 Benefits

• Health insurance
• Paid parental leave
• 401(k) retirement plan
• Meal allowance
• 23 paid days off
• 13 paid flexible holidays