Description
Synthesia, a leading AI video platform, is seeking a Research Engineer specializing in Generative AI, particularly focusing on high-quality, expressive, and real-time synthetic voice creation. The role involves developing and evaluating streaming and speech-to-speech systems, adapting models for various conditioning inputs, implementing post-training optimization techniques, integrating novel architectures like neural codecs, and contributing to new evaluation metrics. This position aims to ensure in-house voice models achieve production-level quality, speed, and robustness.
