# Research Scientist Intern - Multimodal Generative AI and Robotics at Meta

- Company: [Meta](https://meta.com)
- Location: Sunnyvale, CA
- Type: Internship · Internship
- Posted: 2026-10-13
- Apply: https://www.metacareers.com/jobs/1139865145249047
- Page: https://newgrad.ai/jobs/research-scientist-intern-multimodal-generative-ai-and-robot-f2895a6a

## Summary by newgrad.ai

What you'll do:

- Create predictive models combining vision, language, motion, and physical actions.
- Research long-horizon, physically grounded generation techniques for intelligent systems.
- Evaluate performance against current world modeling and video generation standards.
- Use multimodal data to improve robot learning and control capabilities.

What they're looking for:

- Candidates interested in egocentric machine perception and generative AI.
- Ability to commit to internships lasting 12 to 24 weeks.
- Availability for various start dates throughout the year.

## Posting

The Meta Reality Labs Research Team brings together a world-class team of researchers, developers, and engineers to create the future of contextual AI and robotics. The Surreal Vision group at RL Research is seeking exceptional Research Scientists to research and help build the egocentric machine perception functionalities that will underpin future contextual AI-enabled devices.

The Surreal group at Reality Lab Research is seeking outstanding Research Scientist Interns to advance the frontier of egocentric AI. As an intern, you will tackle ambitious research challenges at the intersection of computer vision and natural language, contributing to the development of next-generation intelligent systems.

### Work with researchers to advance frontier generative AI in the following areas:

- Develop unified predictive models that integrate language, vision, human motion, and actions.
- Investigate techniques to enable long-horizon, consistent and physically grounded generation.
- Benchmark against state-of-the-art approaches in world modeling, video generation, and vision–language–action model.
- Leverage multimodal generation to accelerate robot learning and control.
- Build contextual and embodied AI models using large-scale egocentric multimodal datasets

Our internships are twelve (12) to twenty-four (24) weeks long and we have various start dates throughout the year. Some projects may require a minimum of 24 consecutive weeks.

From Meta's public posting, laid out for reading by newgrad.ai with the wording unchanged. Check the original before you apply.

---

More new-grad and intern roles: https://newgrad.ai/llms.txt