Research Scientist – Generative Audio

This is a fully remote position, open to applicants in United Kingdom.

📋 Description

• Conduct innovative research in generative audio utilizing diffusion or flow matching models.

• Execute large-scale experiments leveraging Spotify's infrastructure and audience.

• Develop practical applications that utilize generative technologies.

• Collaborate with a multidisciplinary team to create cutting-edge solutions.

• Participate in the wider research community by publishing results and giving presentations.

⛳️ Requirements

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

• Proven experience in generative modeling, machine learning, music information retrieval, speech processing, audio processing, signal processing, or similar fields.

• Proficiency in vocal/speech synthesis, post-training alignment techniques, or audio-to-audio generation and text-guided music editing.

• Published works at renowned conferences such as ICASSP, ISMIR, INTERSPEECH, ICLR, AAAI, IJCAI, NeurIPS, ICML, CVPR, ECCV, ICCV.

• Strong programming abilities in Python, PyTorch, and NumPy.

🏝️ Benefits

• Health insurance.

• Retirement plans.

• Paid time off.

• Flexible work arrangements.

• Professional development opportunities.