Research Scientist - Generative Audio

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. We invent entirely new listening experiences that center and celebrate artists and creatives. All of our products will put artists and songwriters first, through principles including partnerships with record labels, choice in participation, fair compensation and new revenue, and strengthening artist-fan connection. Conduct groundbreaking research in generative audio using diffusion or flow matching models, with a focus on one or more of the following areas: Vocal Synthesis — research in vocal and speech synthesis, along with related areas such as ML-based audio processing and signal processing; Post-Training — research in post-training techniques for music generation, including preference alignment methods (such as DPO, RLHF, or KTO), reward model design and training, and reinforcement learning to improve output quality, controllability, and human preference adherence; Editing — research in iterative music generation and audio editing, including capabilities such as stem replacement, instrumentation change, mood changes (while preserving content), tempo changes, and structure changes. You will also run large-scale experiments with access to Spotify's infrastructure and audience, create practical applications that harness generative technologies, collaborate cross-functionally with scientists, engineers, product managers, designers, user researchers, and analysts, have direct impact on Spotify products and services, and engage with the research community by publishing, presenting, and attending conferences. Required background includes a Ph.D. in Computer Science, Mathematics, Engineering, or a related field (industry experience helpful); experience in generative modeling, machine learning, music information retrieval, speech/audio/signal processing, probabilistic modeling, or related areas; deep expertise in at least one focus area such as vocal/speech synthesis, post-training alignment techniques (e.g., PPO, GRPO, DPO), or audio-to-audio generation and text-guided music editing; publications at leading conferences; strong coding skills in Python, PyTorch, and NumPy; creativity and interest in turning research into products at scale. The role offers flexibility to work within the EMEA region and operates within Central European and GMT time zones with core collaborative hours; the listing indicates remote work and emphasizes inclusion and accessibility in the hiring process.