PhD Intern: Spatial Localization & Vision-Language

Meta; Boston (MA); On-site; USD 85,000 - 141,000; Full time

Benefits offered by this job

Equal employment opportunity

Accommodation support

Job summary

Meta Reality Labs seeks a Research Scientist Intern in Spatial Reasoning & Localization (PhD). You will research, prototype, and evaluate compact vision-language models that extract spatial evidence and localize against structured maps of indoor/outdoor environments.

Collaboration with researchers and engineers will push forward AR/VR localization capabilities. Ideal candidates are PhD students in CS/EE with experience in vision, ML, VLMs, or visual localization, and proficiency in C++/Python

Qualifications

• PhD candidate in computer science, electrical engineering, or related fields.
• Experience in computer vision, machine learning, vision-language models, or visual localization.
• Strong publication track record in top conferences and familiarity with modern C++/Python.

Responsibilities

• Research and prototype advanced technologies in computer vision and multimodal ML.
• Deliver publishable results with direct impact on Reality Labs products.
• Build datasets, metrics and benchmarks for localization accuracy, latency and cost.
• Analyze efficiency, accuracy, scalability and stability of deployed tech.
• Collaborate across research, prototyping and product deployment lifecycles.

Skills

C++

Python

Computer Vision

PyTorch

Education

PhD candidate in CS/EE

Tools

PyTorch

Job description

Meta Reality Labs seeks a Research Scientist Intern in Spatial Reasoning & Localization (PhD). You will research, prototype, and evaluate compact vision-language models that extract spatial evidence and localize against structured maps of indoor/outdoor environments.

Collaboration with researchers and engineers will push forward AR/VR localization capabilities. Ideal candidates are PhD students in CS/EE with experience in vision, ML, VLMs, or visual localization, and proficiency in C++/Python