Research Scientist, Generative Audio & Music Synthesis

Creandum Advisor LLP; Greater London; Remote; GBP 120,000 - 180,000; Full time

Job summary

Spotify seeks Research Scientists across seniority to advance state‑of‑the‑art generative audio technologies for music. You will conduct groundbreaking research in diffusion or flow matching models, focusing on vocal synthesis, post‑training alignment, and audio editing, while collaborating with engineers, product managers, and designers.

You will publish your findings, attend top conferences, and drive practical applications that enhance listening experiences for millions of users.

Qualifications

• PhD in Computer Science, Mathematics, Engineering or related field.
• Experience in generative modeling, ML, music information retrieval, speech/audio processing.
• Publications at leading conferences (ICASSP, ISMIR, INTERSPEECH, NeurIPS, etc.).
• Strong coding skills in Python, PyTorch and NumPy.

Responsibilities

• Conduct groundbreaking research in generative audio using diffusion or flow matching models.
• Run large‑scale experiments leveraging extensive infrastructure and data.
• Publish findings and present at top conferences; collaborate with cross‑functional teams.
• Contribute to product and tool development at Spotify with scalable research outcomes.

Skills

Python

PyTorch

NumPy

Strong coding skills

Creative problem solver

Education

Ph.D. in Computer Science/Math/Engineering

Job description

Spotify seeks Research Scientists across seniority to advance state‑of‑the‑art generative audio technologies for music. You will conduct groundbreaking research in diffusion or flow matching models, focusing on vocal synthesis, post‑training alignment, and audio editing, while collaborating with engineers, product managers, and designers.

You will publish your findings, attend top conferences, and drive practical applications that enhance listening experiences for millions of users.