This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
Tavus is a research lab pioneering human computing. We’re building AI Humans: a new interface that closes the gap between people and machines, free from the friction of today’s systems. Our real-time human simulation models let machines see, hear, respond, and even look real—enabling meaningful, face-to-face conversations. AI Humans combine the emotional intelligence of humans with the reach and reliability of machines, making them capable, trusted agents available 24/7, in every language, on our terms. We’re looking for a Senior Researcher to join our core AI team. Our ideal partner-in-crime works well in startup environments, is comfortable prioritizing for themselves, and is always down to take calculated risks. We’re moving fast and not looking for people to come along for the ride - we’re looking for people to pave the path.
Job Responsibility:
Lead research efforts on generative video and audio models (ex: text-to-speech, speech-to-speech, audio-to-expression and other speech and multimodal AI topics)
Work with the Applied ML team to help productionize our research
Stay relevant with the latest advancements (and help us create the latest advancements!)
Requirements:
Have proven experience with flow matching, diffusion models, auto regressive networks in the audio domain
Have experience training deep learning models: from medium-sized to large models
Have experience building streaming text-to-speech models or speech-to-speech models
Have strong foundations in audio modeling and demonstrated ability to innovate rapidly through prototyping
Know state-of-the-art architectures in representation learning: audio or image domain, face animation
Have excellent programming skills and be fluent in PyTorch
Show evidence of original research, with publications in top-tier or solid second-tier venues (e.g., CVPR, NeurIPS, BMVC or equivalent)
Be excited about building lifelike, expressive avatars for real-time applications
Nice to have:
Skills in 3D graphics, Gaussian splatting
Other, additional experience with generative models
PhD or equivalent experience preferred
Experience leading research teams
Knowledge of best practices in Software Development