Senior TTS Research Engineer
Core
Optimize neural network algorithms for Text-to-Speech (TTS) inference and generation, integrating components into a flexible pipeline supporting 30+ languages for automotive voice assistants.
Role type
Senior TTS Research Engineer
Builds
TTS engine SDKs, cloud APIs, and automated release pipelines for automotive voice assistants.
Domain
Automotive voice assistants / Speech technology
Deliverable
production ML models | product features
Required skills
TTS system development, C/C++, Python, ML frameworks (PyTorch, TensorFlow), NLP techniques, speech signal processing, autoregressive/non-autoregressive acoustic models, neural vocoders, software release management, version control, ONNX Runtime, TensorRT, TorchScript, zero-shot/one-shot/few-shot voice cloning, emotional TTS systems
Preferred skills
Deep expertise in frontend and backend components, experience with large-scale language support
Technologies
PyTorch, TensorFlow, ONNX Runtime, TensorRT, TorchScript
Responsibilities
Optimize core NN algorithms for speed, integrate TTS components into a multi-language pipeline, implement markups for language optimization, design and maintain emb SDKs, build automation test and release processes, maintain code from RD engineers, write release notes and documentation
Seniority
Senior, hands-on IC