Research Scientist Intern - GenAI, VLM, FlowMatching, Spatial Understanding (PhD)

About Meta Reality Labs

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 visual experiences across Meta's products and AR/VR platforms. We work at the intersection of artificial intelligence, computer vision, and computer graphics. Our research spans generative image and video models, vision-language models, diffusion and flow matching models, multimodal foundation models, diffusion and flow models, neural rendering, novel-view synthesis, and learned 3D and 4D representations of people, objects, and environments. As a Research Scientist Intern, you will help advance the state of the art through an ambitious research project. 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 Generative AI, Computer Vision, and Machine Learning.
• Deliver research results that are both publishable and have a direct impact on Reality Labs or Meta's Family of Apps
• 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.

Minimum Qualifications

• Currently is in the process of obtaining a PhD degree in computer science or related fields
• Experience in one or more areas of Computer Science, such as Generative AI, Vision-Language Models, Computer Vision
• Proven track record of achieving significant results as demonstrated by grants, fellowships, patents, as well as co-authored publications at top-tier conferences
• Experience with Agentic Engineering, Claude Code, Codex
• Experience with C++, Cuda and/or Python
• Experience with deep learning frameworks such as PyTorch

Preferred Qualifications

• 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
• Broad understanding of the full machine vision pipeline from sensors to high-level algorithms
• Mathematical background and understanding of linear algebra, numerical optimization, probabilistic estimation, Understanding of 3D geometry
• Relevant research or software engineering work experiences, including internship, work experience, coding competitions, or widely used contributions in open source repositories