Speech Synthesis Expert
Job Overview:
This is a greenfield opportunity where you'll define the architecture and best practices for training state-of-the-art multilingual text-to-speech TTS models that power our voice AI agents.
1. You'll design, implement ML training inference pipelines for real-time streaming speech generation with sub-100ms response targets.
* The ideal candidate will own the stack from day one and design, implement ML training inference pipelines for speech synthesis tasks including data preparation pre-processing post-processing model selection hyperparameter tuning model deployment monitoring testing fine-tuning evaluation.