Director of Research, Text to Speech
Core
Own the Text-to-Speech (TTS) research program end-to-end, advancing state-of-the-art speech generation and turning research into production models.
Role type
Director of Research (Hands-on IC with leadership)
Builds
Production-grade TTS models and voice agents
Domain
Generative AI, Speech Synthesis, Neural Audio Modeling
Deliverable
production ML models
Required skills
TTS and speech generation expertise, neural audio modeling, research strategy, team leadership, technical tradeoff analysis, experiment design, model evaluation
Preferred skills
Large-scale model training experience, building AI research organizations, sophisticated evaluation systems, external research contributions (publications/patents), startup environment experience
Technologies
Neural audio codecs, speech language models, multimodal models, large-scale neural models
Responsibilities
Define TTS research roadmap and technical direction, drive advances in prosody, expressiveness, and multilingual generation, review research and design experiments, build evaluation and benchmarking systems, lead and develop researchers and tech lead managers, partner with engineering and product on ship-readiness
Seniority
Director, hands-on technical leadership