Leads research in multimodal audio-visual avatar generation for conversational AI, focusing on diffusion models, long-video synthesis, and integrating verbal/non-verbal signals. Requires PhD, 2-3+ years in generative models, PyTorch expertise, and top-tier publications.
AI Researcher develops and fine-tunes large multimodal models for real-time conversational avatars, modeling verbal/non-verbal behaviors with low latency. Requires PhD or equivalent, hands-on experience with VLMs, PyTorch, and deep learning.
Leads research in multimodal audio-visual avatar generation for conversational AI, focusing on diffusion models, long-video synthesis, and integrating verbal/non-verbal signals. Requires PhD, 2-3+ years in generative models, PyTorch expertise, and top-tier publications.
AI Researcher develops and fine-tunes large multimodal models for real-time conversational avatars, modeling verbal/non-verbal behaviors with low latency. Requires PhD or equivalent, hands-on experience with VLMs, PyTorch, and deep learning.