Research Scientist - Generative Audio
Core
Conduct groundbreaking research in generative audio using diffusion or flow matching models to create breakthrough listening experiences for artists and fans.
Role type
Research Scientist (Generative Audio)
Builds
Practical applications of generative technologies for music generation, editing, and synthesis.
Domain
Music technology, Generative AI, Audio Processing
Deliverable
production ML models
Required skills
Generative modeling, Machine learning, Music information retrieval, Speech processing, Audio processing, Signal processing, Probabilistic modeling, Python, PyTorch, NumPy
Preferred skills
Vocal synthesis, Post-training alignment (DPO, RLHF, KTO), Reinforcement learning, Audio-to-audio generation, Text-guided music editing
Technologies
Diffusion models, Flow matching, PyTorch, NumPy
Responsibilities
Run large-scale experiments with access to extensive infrastructure, Create practical applications that harness generative technologies, Collaborate with cross-functional teams, Publish findings and deliver talks at top conferences
Seniority
All levels (Junior to Senior/Principal)
