Research Scientist Intern: Robotics Foundation Models & Agentic RL

Meta; Menlo Park (CA); On-site; USD 55,000 - 83,000; Full time

Job summary

Meta Reality Labs Research seeks a Research Scientist Intern to advance robotics foundation models. The role emphasizes developing agentic RL methods for post-training, leveraging diverse robot datasets and scalable data pipelines. You'll collaborate with researchers to push the capabilities of WAMs and VLAs in embodied AI.

The internship lasts 12–24 weeks with multiple start dates, offering a hands-on opportunity to contribute to cutting-edge algorithmic research in robotics and AI.

Qualifications

• Strong foundation in reinforcement learning and offline RL techniques.
• Experience building scalable training pipelines for large robotics datasets.
• Ability to analyze and improve model performance on post-training tasks.

Responsibilities

• Develop agentic RL algorithms for post-training WAMs and VLAs using large, heterogeneous robot datasets.
• Investigate reward learning, value estimation, and policy optimization for generative action models.
• Address challenges like distribution shift, sparse rewards, and long-horizon credit assignment.
• Build efficient training and data pipelines and study scaling with data, model capacity, and compute.

Skills

Agentic RL

Offline RL

Reinforcement learning

Robotics datasets

Education

PhD

Job description

Meta Reality Labs Research seeks a Research Scientist Intern to advance robotics foundation models. The role emphasizes developing agentic RL methods for post-training, leveraging diverse robot datasets and scalable data pipelines. You'll collaborate with researchers to push the capabilities of WAMs and VLAs in embodied AI.

The internship lasts 12–24 weeks with multiple start dates, offering a hands-on opportunity to contribute to cutting-edge algorithmic research in robotics and AI.