Description
Tavus is hiring an AI Researcher to advance Foundation Multimodal Conversational Models for Conversational Avatars. The role involves researching large multimodal models, developing methods to model and control verbal and non-verbal conversation in real time, experimenting with fine-tuning and conditioning techniques, and partnering with Applied ML to move research from prototype to production. Candidates should have a PhD or equivalent research experience, hands-on experience with large multimodal and generative models, experience fine-tuning VLMs, strong deep-learning knowledge, and PyTorch skills. Preferred locations are San Francisco or London, with remote work available within the United States or Europe.
