Visiting Researcher, Neural 3D Modeling (PhD)

Our mission is to build the spatial intelligence framework and foundation-model family for Meta: ingesting and making all imagery, captures, and map data spatially understandable, queryable, navigable, and transformable. We develop and refine metric expert models in their core capabilities, while our orchestration layer coordinates this intelligence around user intent and leverages it for all spatial reasoning requests.

Our team is addressing technical challenges in foundation spatial AI models, neural 3D modeling, dynamic and semantic scene understanding, and related domains. We're looking for candidates who share a passion for exploring and solving complex problems at the intersection of CV/ML and spatial intelligence.

We are looking for an exceptional candidate currently pursuing a PhD, with a proven track record in developing machine learning algorithms for solving computer vision and graphics problems (e.g., neural rendering, view synthesis, foundation models), as well as an skilled software engineer who can prototype invented algorithms.

This position is short-term employment for candidates currently pursuing a PhD who will work in collaboration with Meta.

Responsibilities

Actively driving and participating in research for foundation spatial AI models and neural 3D modeling Developing efficient neural network models for spatially intelligent, photorealistic, dynamic 3D scenes Contributing to the spatial intelligence framework that makes imagery and map data understandable, queryable, navigable, and transformable Contributing research that can be applied to Meta VR/AR product development Together with our team, working towards a top-tier, scientific publication

Qualifications

Currently has, or is in the process of obtaining a PhD in the field of computer vision, computer graphics, machine learning, or a related field Hands-on knowledge with Neural 3D representations (Neural radiance fields, implicit, explicit & hybrid representations, SDFs, 3D Gaussian Splats) for object-, room-, or city-block sized scenes, neural rendering, etc Experience with PyTorch and Python Experience with neural rendering, novel view synthesis, and 3D reconstruction Experience collaborating with cross-functional and geographically distributed teams to deliver research outcomes Experience developing novel approaches to research problems, as demonstrated by publications, prototypes, or project contributions Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment Demonstrated software engineer experience via previous internships, work experiences, coding competitions, or widely used contributions in open source repositories (e.g. GitHub) Proven track record of achieving significant results as demonstrated by grants, fellowships, patents, as well as first-authored publications at leading conferences (e.g., SIGGRAPH, CVPR, ECCV, ICCV, NeurIPS, ICLR, ICML) or journals (e.g., PAMI, IJCV, JMLR, ToG) Experience in 3D computer vision, graphics, and deep learning models for this domain Experience with 3D representations (NeRFs, 3D Gaussian Splatting), generative models (e.g. diffusion models, GANs), and inverse rendering techniques