Generative Video & Avatar AI Engineer (Real-Time Lip Sync)

IntelliPro; Palo Alto (CA); On-site; USD 180,000 - 200,000; Full time

Job summary

IntelliPro is seeking a Machine Learning Engineer to build the AI systems powering holographic and avatar experiences. You will design end-to-end models that translate audio into expressive, real-time facial animation and full video, optimized for sub-200ms latency at enterprise scale.

You will work with PyTorch and state-of-the-art diffusion-based architectures to deliver multilingual avatar quality and robust lip-sync capabilities, contributing to flagship Physical AI products and scalable

Qualifications

• Hands-on experience with PyTorch and modern deep learning frameworks.
• Background in diffusion models, video generation, or multimodal AI (audio + vision).
• Familiarity with Diffusion Transformers (DiT), 3DGS, or similar generative architectures.
• Experience with talking head synthesis, lip sync, or digital human pipelines.
• Strong fundamentals in computer vision and signal processing.
• Ability to read and implement ideas from recent research papers.

Skills

PyTorch

Deep learning

Diffusion models

Video generation

Multimodal AI

Lip sync

Computer vision

Research comprehension

Tools

Diffusion Transformers (DiT)

3DGS

TensorRT

CUDA

Job description

IntelliPro is seeking a Machine Learning Engineer to build the AI systems powering holographic and avatar experiences. You will design end-to-end models that translate audio into expressive, real-time facial animation and full video, optimized for sub-200ms latency at enterprise scale.

You will work with PyTorch and state-of-the-art diffusion-based architectures to deliver multilingual avatar quality and robust lip-sync capabilities, contributing to flagship Physical AI products and scalable