Description
Zyphra, an AI company in Palo Alto, CA, is seeking a Research Engineer to join their Audio Team and develop open-source text-to-speech and audio models. The role involves the entire model training process, from data gathering and processing to designing novel architectures and training methodologies. The ideal candidate will have strong research taste, implementation skills, and the ability to collaborate in a fast-paced research environment. Bonus qualifications include expertise in training audio models, experience with audio autoencoders, and proficiency with PyTorch and Python.
