The role involves developing and improving TTS/Voice Generation models, training, fine-tuning, evaluating speech models, and collaborating across research, engineering, and product teams in a fast-paced startup environment.

Lead design, training, fine-tuning, evaluation, and production deployment of TTS/voice-generation models. Translate research into reliable, low-latency production systems, define ML best practices, and collaborate across research, engineering, and product to drive execution.