Research Scientist Intern, Spatial Reasoning & Localization (PhD)

Meta Reality Labs brings together researchers and engineers to invent the future of visual computing.

Our teams develop technologies that enable people to capture, create, understand, and interact with immersive visual experiences across Meta’s products and AR/VR platforms. We work at the intersection of artificial intelligence, computer vision, multimodal language models, and maps.

Our research spans localization, vision-language models, scene text and landmark understanding, and spatial reasoning grounded in maps and floor plans, so that devices such as AI glasses can understand where people are, indoors and outdoors.

As a Research Scientist Intern, you will help advance the state of the art in a fast, lightweight VLM driven visual localizer that reasons over semantic and geometric evidence in images and structured map representations, estimating where the image was taken: the place, the floor, and the camera's position and heading.

You will collaborate with researchers and engineers to develop new models, representations, datasets, and evaluation methods—with opportunities to publish your work and influence future products used by people around the world.

Responsibilities

Research, develop and prototype advanced technologies in the domain of Computer Vision, Multimodal Machine Learning, and Visual Localization, such as compact vision-language models that extract structured spatial evidence from images and localize them against structured map representations of indoor and outdoor environments.
Deliver research results that are both publishable and have a direct impact on Reality Labs or Meta’s Family of Apps.
Build datasets, metrics, and benchmarks for localization accuracy, latency, and cost, and compare against frontier vision-language models.
Analyze the efficiency, accuracy, scalability, and stability of currently deployed technologies to identify opportunities for impact through novel research.
Collaborate with team members throughout the lifetime of a project, from research to prototyping to deploying products.

Qualifications

Currently is in the process of obtaining a PhD degree in computer science, electrical engineering, or related fields
Experience in one or more areas of Computer Science, such as Computer Vision, Machine Learning, Vision-Language Models, Visual Localization
Proven track record of achieving significant results as demonstrated by grants, fellowships, patents, as well as co-authored publications at top-tier conferences such as CVPR, ICCV, ECCV, NeurIPS, ICLR, or ICML
Experience with modern C++ and/or Python
Experience with deep learning frameworks such as PyTorch Intent to return to their degree program after the completion of the internship
Interpersonal experience: cross-group and cross-culture collaboration
Strong communication skills and ability to convey research ideas to a broad audience
Research experience in visual localization, visual place recognition, image geolocalization, scene text recognition, or camera pose estimation
Mathematical background in linear algebra, numerical optimization, and probabilistic estimation, and understanding of 3D geometry and camera models
Experience training or fine-tuning vision-language models, including distillation, reinforcement learning, or efficient inference (for example quantization or structured outputs)
Familiarity with map and place data, floor plans, or positioning signals such as GPS and Wi-Fi
Relevant research or software engineering work experiences, including internship, work experience, coding competitions, or widely used contributions in open source repositories