Research Scientist Intern - Spatial Reasoning & Localization
MetaAdded 5h ago
Save this job and browse the whole board.
No credit card needed
Quick summaryby newgrad.ai
What you'll do
- Develop lightweight visual localizers using vision-language models.
- Estimate camera position, floor level, and location from images.
- Create new datasets, models, and evaluation methods.
- Collaborate with engineers to influence future AR/VR products.
What they're looking for
- Experience with computer vision and spatial reasoning.
- Proficiency in multimodal language models and mapping.
- Ability to conduct research on geometric and semantic evidence.
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.
From Meta's public posting, laid out for reading by newgrad.ai with the wording unchanged. Check the original before you apply.
Apply on Meta's site.
Apply nowListing wrong or expired, or you're the employer and want it removed? Let us know.