About the Role:

We are looking for ML Research Engineers who are passionate about generative models for music creation. In particular, we are looking for people who can explore new ideas and architectures for music generation models; highly creative people who straddle research and engineering and who are motivated to push the boundaries of generative music research, not just in state-of-the-art performance, but also in balancing performance and resource usage. You will have access to state-of-the-art, high-performance computing resources, and you will work alongside top researchers and engineers to truly make an impact in the fast growing world of generative AI.

Responsibilities:

• Work with the rest of the research team and the open-source community on developing the next generation of generative audio models
• Prototype and productionize model architecture improvements and new features
• Maintain and innovate on open-source code repositories for generative AI audio models, including custom model code, training code, and fine-tuning code
• Work with Product, Engineering and Commercial teams on model deployment and customized training
• Create interactive demos and interfaces for generative models, demonstrating simple use cases in an intuitive and fun way
• Optimize model architectures and inference code for performance on consumer devices
• Publish results at top conferences, in journals, and in blog posts
• Keep up to date with the latest research advancements in the field and work them into open-source repos, reimplementing as needed to ensure an open license

Qualifications:

• 3+ years working on machine learning projects, including training, fine tuning and refining models
• Publication of papers, projects, and blog posts that had a high impact in generative AI
• Experience maintaining high-quality, well-documented open-source code repositories for AI models
• Experience with music generation models, preferably working in the time domain (Jukebox, SampleRNN, RAVE, etc.)
• Ability to iterate quickly on public code-bases with attention to backwards compatibility, usability, and readability
• Experience with Python scientific stack, PyTorch, and creating Jupyter/Colab notebooks
• Ability to communicate machine learning concepts and results effectively through writing and visualization
• Experience training and/or deploying ML models with Amazon AWS (Sagemaker a plus) or Google Cloud
• Experience with data engineering, including cleaning and maintaining large heterogeneous datasets
• Experience building interactive web demos that serve generative ML models
• Experience with the open-source ML ecosystem (HuggingFace, W&B, etc.)
• Experience with Linux and command line tools
• Familiarity with digital signal processing and audio engineering concepts
• Experience with Python audio processing libraries such as librosa, torchaudio, or similar

Equal Employment Opportunity:

We are an equal opportunity employer and do not discriminate on the basis of race, religion, national origin, gender, sexual orientation, age, veteran status, disability or other legally protected statuses.