Research Scientist - Generative Audio

Research Scientist at Spotify in London focusing on generative audio. The role involves conducting groundbreaking research in generative audio using diffusion or flow matching models, with a focus on vocal synthesis and post-training techniques for music generation.

Skills and focus areas

• generative audio
• vocal synthesis
• speech synthesis
• ml-based audio processing
• signal processing
• post-training techniques
• preference alignment methods
• reward model design
• diffusion models
• flow matching models