Deep Learning Scientist, Speech Synthesis

08/06/26 The hiring manager is looking for people with experience working with autoregressive models, diffusion and flow matching models, FSQ and RVQ codec models, and full-duplex speech-to-speech models. Deep Learning Scientist – Speech Synthesis Update on 07/22/26: No PHD is need just focus on seeking candidates with deep, hands-on expertise in Text-to-Speech (TTS), including experience developing and working with modern SOTA architectures and models. It is essential that their TTS background…