AI Researcher (Multimodal Audio/Video Generation)
Tavus · San Francisco
Applied AIonsitesenior
At a glance
Highlights
- Lead research on audio-visual avatar generation for conversational settings.
- Build AI humans that see, hear, and respond in lifelike face-to-face conversation.
- Partner with engineering to bring avatar research into real-world production.
Ideal candidate
A generative media researcher who thrives in ambiguity and loves pushing human-AI interaction forward. You mentor others, turn ideas into real products, and care about empathetic, lifelike conversational experiences.
Requirements
- PhD or equivalent research experience plus 2-3+ years applying generative models at scale
- Expertise in diffusion models and latest efficiency techniques
- Experience in multimodal generation across video, audio and language
- Proven innovation in long-video generation and/or audio generation
- Fluent in PyTorch and GPU-optimized workflows
- Publication record in top-tier venues such as CVPR, NeurIPS, BMVC, ICASSP
- Experience leading research activities or mentoring teams
- remote policy
- Remote within U.S. or Europe considered for exceptional candidates
Lab profile
About Tavus
Building real-time human simulation models for lifelike conversational AI video agents.
What they build
- Conversational Video Interface (CVI)
- AI Humans real-time video agents
- Raven perception model
Known for
- Real-time human simulation
- Multimodal perception and generation
- Low-latency conversational video infrastructure
- Emotionally intelligent lifelike avatars
Key facts
- Series B
- 90–100 people
- Offices in San Francisco and London
Posted · Last seen