Research Scientist Intern, 3D Machine Perception and Generative AI (PhD)

Meta - Redmond, WA

Full-time - Intern

Redmond, WA

Web Search Portals, Libraries, Archives, and Other Information Services

About the position

The Meta Reality Labs Research Team is at the forefront of innovation in augmented reality (AR) and virtual reality (VR), bringing together a world-class team of researchers, developers, and engineers. The Surreal Vision group within this team is seeking exceptional Research Scientists to contribute to groundbreaking research in egocentric machine perception functionalities and the development of digital twins of 3D scenes. These advancements are crucial for the future of VR and contextual-AI-enabled AR devices. As a research intern, you will engage with cutting-edge research problems, focusing on novel computer vision and machine learning techniques that will shape the next generation of immersive technologies. In this role, you will collaborate with researchers to enable their work across various research disciplines. Your responsibilities will include researching novel object and scene reconstruction methods to recover the physical properties or functionalities of real-world objects and environments through egocentric machine perception. You will also be tasked with building related datasets for physical scene understanding, estimating egocentric human states, and understanding motion using multimodal data. Additionally, you will work on egocentric 3D reconstruction and 3D scene understanding, which includes tasks such as 3D segmentation and 3D bounding box detection for both static and dynamic scenes. The internship duration ranges from twelve (12) to twenty-four (24) weeks, with various start dates available throughout the year.

Responsibilities

• Plan and execute cutting-edge research and development to advance the state-of-the-art in machine perception, state estimation, reconstruction, and rendering of 3D objects and scenes.
• Collaborate with other researchers and engineers across machine perception teams at Meta to develop experiments, prototypes, and concepts that advance the state-of-the-art in AR/VR and AI systems.
• Work with the team to help design, setup, and run practical experiments and prototype systems related to large-scale high-quality sensing and machine reasoning.

Requirements

• Currently has, or is in the process of obtaining a PhD degree in the domain of computer vision, computer graphics, 3D machine perception, or machine learning.
• Knowledge and hands-on experience working with 3D and projective geometry, in addition to image-space computer vision.
• Hands-on experience implementing 3D computer vision algorithms as well as end-to-end training of ML models from data collection and design to evaluation.
• Experience working within Python environments such as PyTorch.
• Experience working in a Unix environment.
• Interpersonal experience: cross-group and cross-culture collaboration.
• Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment.

Nice-to-haves

• Proven track record of achieving significant results as demonstrated by grants, fellowships, patents, as well as first-authored publications at leading workshops or conferences such as CVPR, ECCV/ICCV, SIGGRAPH/SIGGRAPH Asia, ICLR, and NeurIPS.
• Strong track record of published research in the fields of neural reconstruction, inverse rendering, neural rendering, object reconstruction and tracking, generative modeling.
• Strong programming experience using Python and PyTorch.
• Demonstrated software engineering experience via an internship, work experience, coding competitions, or widely used contributions in open source repositories (e.g. GitHub).
• Availability for a 24 consecutive week internship.
• Intent to return to a degree program after the completion of the internship.

Benefits

• $7,500/month to $11,333/month + benefits