Tavus is looking for an AI Researcher (Voice) to lead our research efforts on generative video and audio models for lifelike, expressive avatars in real-time applications. You will be a key member of our Core AI team, helping to build the human layer of AI to make human-AI interaction as natural as face-to-face interaction.

What You'll Do

Lead research efforts on generative video and audio models, such as text-to-speech, speech-to-speech, and audio-to-expression.
Work with the Applied ML team to help productionize research.
Stay relevant with the latest advancements in AI and help create them.

What We're Looking For

Proven experience with flow matching, diffusion models, and auto regressive networks in the audio domain.
Experience training deep learning models from medium-sized to large models.
Experience building streaming text-to-speech models or speech-to-speech models.
Strong foundations in audio modeling and demonstrated ability to innovate rapidly through prototyping.
Knowledge of state-of-the-art architectures in representation learning for audio or image domains, including face animation.
Excellent programming skills and fluency in PyTorch.
Evidence of original research, with publications in top-tier or solid second-tier venues such as CVPR, NeurIPS, or BMVC.
Excitement about building lifelike, expressive avatars for real-time applications.

Nice to Have

Skills in 3D graphics and Gaussian splatting.
Additional experience with generative models.
PhD or equivalent research experience.
Experience leading research teams.
Knowledge of best practices in software development.

Technical Stack

PyTorch

Team & Environment

You will be part of the Core AI team at Tavus, a group dedicated to advancing the state of generative media. Our work is driven by our team, and our success is shared by all.