Responsibilities

• Partner with Researchers, Machine Learning Engineers and Product and Engineering teams
• Conduct ML model training, benchmarking, testing and deployment of multi modal tracking, reconstruction and animation models.
• Create productionalized Python code, using Pytorch frameworks.
• Work with 3DMMs and statistical models for training and inference
• Work with 2D and 3D image and video for tracking and reconstruction.

Qualifications

• On going MS or Ph.D student in Visual Computing, Computer Vision, Computer Graphics, 3D Vision, or related field industry or research experience with deep learning and computer vision
• Extensive experience with PythonFamiliar with linear algebra, and numerical optimization
• Experience with cloud platforms such as GCP, Azure, or AWS
• Monocular 3D Facial Tracking
• Generative models for face reconstruction
• Experience with machine learning and deep learning and modern 2D and 3D Vision.
• Proficiency in applied research tasks: Maintaining and versioning production code and datasets.
• Creating metrics and benchmarking
• Improving the efficiency of the solution
• Ability to conduct proactive and independent applied research beyond expectations
• Experience with CV tools e.g. OpenCV, scikit, numpy, etc
• Experience with differentiable rendering pipelines, such as PyTorch3D, or Taichi Graphics.
• Familiar with 3DMM and statistical models
• Experience with developing machine and deep learning approaches as well as modern 2D and 3D Vision tools.

Preferred Qualifications

• MS (with experience) or Ph.D. in Computer Vision, Computer Graphics, 3D Vision, or related field
• Experience developing tools or solutions at scale for multi-modal or audio-driven visual systems in AR/VR or VFX
• Experience with C++ or CUDA
• Familiarity with Transformer, CNN, and GAN architectures
• Published work in top-tier CV and Graphics conferences e.g. ICCV, CVPR, SIGGRAPH

PI250282210