Description
The role focuses on generative audio systems across models, evaluation, and data. Responsibilities include designing experiments to distinguish genuine progress from noise, building evaluation and dataset pipelines, and balancing quality, latency, reliability, and cost. The position seeks ownership in ambiguous problem spaces, interest in audio, music, and generative modeling, strong evaluation and reproducibility habits, and fluency in Python and PyTorch or similar tools. Relevant experience includes generative modeling, audio machine learning, and multi-GPU or distributed training. Benefits include high ownership, AI-driven music innovation, scalable infrastructure work, competitive compensation and equity, and flexible work arrangements.
