About the Role

This is a PhD-level research scientist internship focused on advancing 3D world modeling, robotics, and generative AI for AR/VR. The intern will develop novel computer vision and machine learning techniques, collaborate on cutting-edge research, and work on egocentric world models and multimodal generation. The role involves prototyping, experimentation, and contributing to scientific publications.

Key Responsibilities

• Plan and execute cutting-edge research in machine perception, 3D reconstruction, and rendering
• Collaborate with researchers to develop experiments and prototypes for AR/VR and AI systems
• Design, setup, and run practical experiments related to large-scale sensing and machine reasoning
• Develop novel egocentric world models for action-conditioned video synthesis
• Establish multimodal generation models including RGB video, 2D/3D flow, and depth maps

Required Skills & Qualifications

Must Have:

• Currently has or is in the process of obtaining a PhD in computer vision, computer graphics, 3D machine perception, or machine learning
• Knowledge and hands-on experience with 3D and projective geometry and image-space computer vision
• Hands-on experience implementing 3D computer vision algorithms and end-to-end training of ML models
• Experience working within Python environments such as PyTorch and in a Unix environment
• Must obtain work authorization in the country of employment at the time of hire

Nice to Have:

• Proven track record of significant results demonstrated by grants, fellowships, patents, or first-authored publications at leading conferences
• Strong track record of published research in neural reconstruction, inverse rendering, neural rendering, object reconstruction, tracking, or generative modeling
• Strong programming experience using Python and PyTorch
• Demonstrated software engineer experience via internships, work experience, coding competitions, or open-source contributions
• Intent to return to a degree-program after the internship and experience working cross-functionally in a team