AI Researcher (Multimodal Audio/Video Generation)
San Francisco
Workplace: OnsiteFull timeFunction: Research & Scientific (R&D)Experience: 2-3 yearsEducation: phdSkills: ["PyTorch","GPU-accelerated workflows","Communication","Mentoring"]Lead research in audio-visual avatar generation, pushing multimodal generative models toward realistic, conversational AI. Design diffusion-based, long-video and audio-visual systems synced with conversation flow, translating research into production with Applied ML and engineering. Mentor researchers, publish impactful work, and shape how humans interact with AI Humans at Tavus.
Loading
Loading job details...
Preparing the role view and application actions.

