Description
Tavus is hiring a Senior AI Researcher to lead research on audio-visual avatar generation, including neural avatars and talking heads in conversational settings. The role involves designing coupled verbal and non-verbal models, advancing diffusion and long-video generation, translating research into production with Applied ML and engineering, mentoring researchers, and publishing work. Candidates should have a PhD or equivalent research experience, 2–3+ years of hands-on generative-model experience, expertise in diffusion and multimodal generation, strong PyTorch and GPU skills, and a publication record. Preferred locations are San Francisco (hybrid) or London, with remote work within the United States or Europe considered for exceptional candidates.
