AI Researcher (Multimodal Audio/Video Generation)
Job Description
- Experience with long-video or audio generation
- Skills in 3D graphics, Gaussian splatting, or large-scale training setups
- Broader exposure to generative models and rendering
- Familiarity with software engineering best practices
- Publications in top-tier or respected venues (CVPR, NeurIPS, BMVC, ICASSP, etc.)
- PhD (or near completion) in a relevant field, or equivalent hands-on research experience
- Experience applying image/video generation models in practice
- Strong foundations in generative modeling and rapid prototyping
- Deep familiarity with diffusion models, including recent advances in efficiency
- Good understanding of video-language models and multimodal generation
- Proficiency in PyTorch and GPU-based inference
About Us
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.
Imagine a therapist anyone can afford. A personal trainer that adapts to your schedule. A fleet of medical assistants that can give every patient the attention they need. With Tavus, individuals, enterprises, and developers can all build AI Humans to connect, understand, and act with empathy at scale.
We’re a Series A company backed by world-class investors including Sequoia Capital, Y Combinator, and Scale Venture Partners.
Be part of shaping a future where humans and machines truly understand each other.
The Role
We’re looking for an AI Researcher to join our core AI team and push forward the science of audio-visual avatar generation. If you thrive in high-speed startup environments, enjoy experimenting with generative models, and love seeing your research ship into production then you’ll feel right at home.
Your Mission 🚀
- Research and develop audio-visual generation models for conversational agents (e.g. Neural Avatars, Talking-Heads).
- Focus on models that are tightly coupled with conversation flow, ensuring verbal and non-verbal signals work seamlessly together.
- Experiment with diffusion models (DDPMs, LDMs, etc.), long-video generation, and audio generation.
- Collaborate with the Applied ML team to bring your research into real-world production.
- Stay ahead of the latest advancements in multimodal generation — and help shape the next wave.
You’ll Be Great At This If You Have:
- A PhD (or near completion) in a relevant field, or equivalent hands-on research experience.
- Experience applying image/video generation models in practice.
- Strong foundations in generative modeling and rapid prototyping.
- Deep familiarity with diffusion models, including recent advances in efficiency.
- Good understanding of video-language models and multimodal generation.
- Proficiency in PyTorch and GPU-based inference.
Nice-to-Haves
- Experience with long-video or audio generation.
- Skills in 3D graphics, Gaussian splatting, or large-scale training setups.
- Broader exposure to generative models and rendering.
- Familiarity with software engineering best practices.
- Publications in top-tier or respected venues (CVPR, NeurIPS, BMVC, ICASSP, etc.).
Location
Preferred: San Francisco (hybrid) or London (office opening soon). Remote within U.S. or Europe available for exceptional candidates.
