Research Scientist in Generative Audio

Job Summary

Seeking a full-time remote Research Scientist in Generative Audio, the successful candidate will conduct groundbreaking research in generative audio technologies, focusing on vocal synthesis, post-training techniques, and audio editing while collaborating with cross-functional teams to create innovative listening experiences.

Key responsibilities:

• Conduct research in vocal synthesis, post-training methods, and iterative audio editing
• Run large-scale experiments utilizing Spotify's infrastructure and audience
• Collaborate with scientists, engineers, and product teams to develop practical applications of generative technologies

Required qualifications:

• Ph.D. in Computer Science, Mathematics, Engineering, or a related field
• Experience in generative modeling, machine learning, or audio processing
• Deep expertise in vocal/speech synthesis, post-training alignment, or audio-to-audio generation
• Publications at leading conferences in relevant fields
• Strong coding skills in Python, PyTorch, and NumPy