Research Staff, Voice AI Foundations

Tech Stack

Responsibilities

• Pioneer the development of Latent Space Models (LSMs) to solve fundamental data, scale, and cost challenges for voice AI.
• Build next-generation neural audio codecs for extreme compression and high-fidelity reconstruction across diverse audio corpora.
• Develop steerable generative models to synthesize diverse human speech from latent representations.
• Design embedding systems to factorize latent space into interpretable dimensions (speaker, content, style, environment, channel effects) for precise control and data amplification.
• Leverage latent recombination to generate synthetic audio data at scale, enabling multimodal speech-to-speech systems that understand and respond empathetically to any human.

Benefits

• Health Insurance

Culture

Requirements