Senior TTS Research Engineer(m/w/x)

Description

In this role, you will enhance TTS technology by optimizing algorithms and integrating components for a multilingual pipeline. Your work will involve designing SDKs, maintaining code, and ensuring quality through testing and documentation.

Requirements

• •3+ years of hands-on experience in TTS system development
• •Proficiency in C/C++ and Python
• •Mastery of ML frameworks (PyTorch, TensorFlow, etc)
• •Background in NLP techniques and/or speech signal processing
• •Basic understanding of autoregressive/non-autoregressive acoustic models
• •Rich experience on software release and version control
• •Experience with ONNX Runtime, TensorRT, or TorchScript
• •Experience with zero-shot/one-shot/few-shot voice cloning
• •Fluent English, especially written
• •Basic knowledge of information security and data privacy requirements

Tasks

• •Optimize core neural network algorithms for faster inference and generation
• •Integrate various TTS components into a flexible pipeline for 30+ languages
• •Implement markups to optimize the TTS engine for different languages and applications
• •Design, implement, and maintain the emb SDK for multiple platforms and cloud APIs
• •Establish automation testing and release processes to meet KPIs like latency and RTF
• •Maintain code developed by research and development engineers
• •Write well-structured release notes, SDK, and API documentation

Tools & Technologies