Research Scientist Intern

Responsibilities:

• Participating in cutting-edge research in 3D-controlled dynamic face neural rendering. 
• Solving real problems in enabling audio-driven photorealistic talking head synthesis. 
• Developing efficient deep neural network models for photorealistic neural rendering.
• Collaborating with and supporting other researchers across various departments.
• Pushing the state-of-the-art research from top-tier conferences (e.g. CVPR, ICCV, ECCV, SIGGRAPH, etc.) 

Requirements:

• On-going Ph.D. in Visual Computing, Computer Vision, Machine Learning, or a related field
• Proven track record of first-authored publications at leading conferences (e.g., SIGGRAPH, CVPR, ECCV, ICCV, NeurIPS, ICLR, ICML) or journals (e.g., PAMI, IJCV, JMLR, ToG)
• 2+ years experience with building systems based on Computer Graphics, Computer Vision, or Machine Learning methods.
• Strong experience with deep learning and computer vision in one or more of the following fields:
• Generative Neural Networks (Diffusion Models, GAN, VAE, etc. )
• Neural networks and transfer learning
• Un-supervised or self-supervised learning
• Few/zero-shot learning for image synthesis
• Neural talking head synthesis
• Domain adaptation techniques for image face synthesis
• 3D computer vision
• Proficiency with deep learning frameworks such as PyTorch.
• Proficiency in statistical methods and numerical optimization
• Interest in building real-world tools with product impact

Nice to Have:

• Experience with 3DMM and statistical face models
• Experience with Transformer, CNN, GAN, and Diffusion model architectures
• Experience with differentiable rendering pipelines, such as PyTorch3D
• Interpersonal experience: cross-group and cross-culture collaboration