Tavus is looking for an AI Researcher (Rendering) to lead our research efforts on generative video models for human avatar rendering and communication. You will work closely with the Applied ML team to productionize research and help us stay at the forefront of advancements in this space. Our mission is to make human-AI interaction as natural as face-to-face interaction.

What You'll Do

Lead research efforts on generative video models, including Neural Avatars, Talking-Head synthesis, Lip-sync, and other low-level computer vision topics.
Work with the Applied ML team to help productionize our research.
Stay relevant with the latest advancements and contribute to creating them.

What We're Looking For

You are, at a minimum, a recent or soon-to-be PhD graduate, or have 2–3 years of hands-on experience applying diffusion models in practice.
You have strong foundations in generative modeling, ideally with a focus on image or video synthesis, and a demonstrated ability to innovate rapidly through prototyping.
You have deep experience with diffusion models (DDPMs, LDMs, etc.) for either image or video domains.
You are fluent in PyTorch and comfortable working with GPU-based inference.
You show evidence of original research, with publications in top-tier or solid second-tier venues (e.g., CVPR, NeurIPS, BMVC).
You are excited about building lifelike, expressive avatars for real-time applications.

Nice to Have

PhD or equivalent experience.
Skills in 3D graphics, Gaussian splatting, or large-scale training setups.
Additional experience with generative models and rendering.
Experience leading research teams.
Knowledge of best practices in Software Development.

Technical Stack

PyTorch
GPU-based inference
Diffusion models (DDPMs, LDMs)

Team & Environment

You will join our Core AI team. At Tavus, we are building the human layer of AI. We are not looking for cultural fits; we are looking for culture creators. Diversity is what drives our success—it’s at the core of how we hire, communicate, and work.