Research Scientist - Generative Audio

About the Role

We are seeking Research Scientists (across all levels of seniority) to join our Artist-First AI Music Lab. Our team pioneers and advances state-of-the-art generative technologies for music that create breakthrough experiences for fans and artists, centering and celebrating artists and creatives.

What You'll Do

• Conduct groundbreaking research in generative audio using diffusion or flow matching models, focusing on areas such as:

- Vocal Synthesis: Research in vocal and speech synthesis, along with ML-based audio processing and signal processing.
- Post-Training: Research in post-training techniques for music generation, including preference alignment methods (DPO, RLHF, KTO), reward model design and training, and reinforcement learning.
- Editing: Research in iterative music generation and audio editing, including stem replacement, instrumentation change, mood changes, tempo changes, and structure changes.

• Run large-scale experiments with access to Spotify's extensive infrastructure and an audience of over 700 million monthly active users.
• Create practical applications that harness generative technologies and push the boundaries of listening experiences.
• Collaborate as part of a cross-functional team of scientists, engineers, product managers, designers, user researchers, and analysts.
• Engage with the broader research community by publishing findings, delivering talks, and attending top conferences.

Who You Are

• You have a Ph.D. in Computer Science, Mathematics, Engineering, or a related field. Previous industry experience is helpful.
• You have experience in generative modeling, machine learning, music information retrieval, speech processing, audio processing, signal processing, probabilistic modeling, computer vision, or related areas.
• You have deep expertise in vocal/speech synthesis, post-training alignment techniques (e.g., PPO, GRPO, DPO), or audio-to-audio generation and text-guided music editing.
• You have publications at leading conferences such as ICASSP, ISMIR, INTERSPEECH, ICLR, AAAI, IJCAI, NeurIPS, ICML, CVPR, ECCV, ICCV, or related venues.
• You have strong coding skills in Python, PyTorch, and NumPy.
• You are a creative problem solver passionate about turning research ideas into scaled products.
• You can explain complex topics in simple terms and build strong relationships with colleagues and stakeholders.

Where You'll Be

• Remote within the North America region where Spotify has a work location.
• The team operates within Eastern Standard Time (EST) with core collaboration hours between EST 9am-12pm (CET 3pm-6pm).