Research Staff, Voice AI Foundations

Strong mathematical foundation in statistical learning theory (self-supervised and multimodal learning) Deep expertise in foundation model architectures and scaling training across modalities Proven ability to bridge theory and practice (derive mathematical formulations and implement efficiently) Demonstrated ability to build data pipelines for massive datasets Track record of designing controlled experiments Experience optimizing models for real-world deployment (hardware constraints, efficiency techniques) History of open-source contributions or research publications in speech/language AI

Build next-generation neural audio codecs Pioneer steerable generative models for speech synthesis Develop embedding systems for interpretable latent spaces Leverage latent recombination for synthetic audio data generation Train multimodal speech-to-speech systems Design model architectures, training schemes, and inference algorithms adapted for hardware