About the role
About Us
Tavus is an innovative research lab at the forefront of human computing technology. Our mission is to create AI Humans, advanced interfaces that bridge the gap between individuals and machines, eliminating the friction found in current systems. Our real-time human simulation models empower machines to see, hear, respond, and appear realistic, facilitating genuine, face-to-face conversations. With AI Humans, we blend the emotional intelligence inherent in humans with the extensive reach and reliability of machines, enabling them to serve as capable and trusted agents available 24/7, capable of communicating in any language.
Envision a therapist accessible to everyone, a personal trainer that tailors sessions to your schedule, or a fleet of medical assistants dedicated to providing personalized attention to every patient. Tavus enables individuals, enterprises, and developers to create AI Humans that connect, empathize, and act with understanding on a large scale.
Backed by prestigious investors like Sequoia Capital, Y Combinator, and Scale Venture Partners, we are a Series A company ready to shape the future of human-machine interaction.
Join us in transforming a future where humans and machines genuinely comprehend one another.
The Role
We are seeking a passionate AI Researcher to join our core AI team and advance the science of audio-visual avatar generation. If you thrive in dynamic startup environments, enjoy experimenting with generative models, and are excited to see your research translated into production, you will find a welcoming home here.
Your Mission
Conduct research and develop cutting-edge audio-visual generation models for conversational agents (e.g., Neural Avatars, Talking Heads).
Focus on models that intricately align with conversation flows, ensuring seamless integration of verbal and non-verbal cues.
Experiment with diffusion models (DDPMs, LDMs, etc.), long-video generation, and audio synthesis.
Collaborate closely with the Applied ML team to transition your research into practical applications.
Stay updated on the latest breakthroughs in multimodal generation and contribute to the evolution of this field.
You Will Excel If You Have:
A PhD (or nearing completion) in a relevant discipline, or equivalent hands-on research experience.
Proficiency in applying image/video generation techniques and a solid understanding of machine learning principles.
