Visiting Researcher, Neural 3D Modeling (PhD)

Meta; Zürich; On-site; CHF 90,000 - 130,000; Part time

Job summary

Meta in Zürich is seeking a Visiting Researcher on a short-term contract to join the Reality AI Research team. The role focuses on building foundation spatial AI models and neural 3D modeling, contributing to a framework that makes imagery and map data spatially understandable, queryable, navigable, and transformable.

The ideal candidate is pursuing a PhD with a track record in CV/ML, capable of prototyping new algorithms, and collaborating with distributed teams to drive significant research

Qualifications

• Pursuing or holding a PhD in CV, graphics or ML.
• Experience with neural 3D representations and neural rendering.
• Proficiency in PyTorch and Python.
• Strong collaboration across distributed teams.
• Evidence of research impact via publications or prototypes.
• Authorized to work in the country at hire.

Responsibilities

• Actively drive and participate in research for foundation spatial AI and neural 3D modeling.
• Develop efficient neural network models for spatially intelligent, photorealistic, dynamic 3D scenes.
• Contribute to the spatial intelligence framework for imagery and map data.
• Contribute research applicable to Meta VR/AR product development.
• Work with the team toward top-tier scientific publications.

Skills

PhD in CV/Graphics/ML

Neural 3D representations

Neural rendering

PyTorch

Python

Cross-functional collab

Publications/prototypes

Work authorization

Education

PhD in CV/Graphics/ML

Job description

Summary:

Meta is seeking a Visiting Researcher through a short-term contract to join the Reality AI Research team. 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.

Required Skills:

Visiting Researcher, Neural 3D Modeling (PhD) Responsibilities:

1. Actively driving and participating in research for foundation spatial AI models and neural 3D modeling

2. Developing efficient neural network models for spatially intelligent, photorealistic, dynamic 3D scenes

3. Contributing to the spatial intelligence framework that makes imagery and map data understandable, queryable, navigable, and transformable

4. Contributing research that can be applied to Meta VR/AR product development

5. Together with our team, working towards a top-tier, scientific publication

Minimum Qualifications:

1. 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

2. 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

3. Experience with PyTorch and Python

4. Experience with neural rendering, novel view synthesis, and 3D reconstruction

5. Experience collaborating with cross-functional and geographically distributed teams to deliver research outcomes

6. Experience developing novel approaches to research problems, as demonstrated by publications, prototypes, or project contributions

7. Must obtain work authorization in the country of employment at the time of hire, and maintain ongoing work authorization during employment

Preferred Qualifications:

1. Demonstrated software engineer experience via previous internships, work experiences, coding competitions, or widely used contributions in open source repositories (e.g. GitHub)

2. 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)

3. Experience in 3D computer vision, graphics, and deep learning models for this domain

4. Experience with 3D representations (NeRFs, 3D Gaussian Splatting), generative models (e.g. diffusion models, GANs), and inverse rendering techniques

Industry:

Internet