Research Scientist Intern, Robotics Foundation Models, Agentic RL (PhD)

Facebook, Inc.; 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

Research Scientist Intern, Robotics Foundation Models, Agentic RL (PhD)# Research Scientist Intern, Robotics Foundation Models, Agentic RL (PhD)Menlo Park, CA Research+ 2 moreApply nowMeta Reality Labs Research is a team of researchers and engineers pushing the frontier of AI and robotics. Our team is building the next generation of world action models (WAMs) and vision-language-action models (VLAs) for robotic manipulation. We are seeking a Research Scientist Intern to develop scalable offline reinforcement learning methods for post-training these models.Interns in this role will conduct fundamental and applied research to advance foundation models for robotics, with a focus on post-training. You will collaborate with research scientists and engineers to develop new algorithms, build and evaluate model capabilities, and contribute to the next generation of embodied AI.Our internships are twelve (12) to twenty-four (24) weeks long and we have various start dates throughout the year.---## Research Scientist Intern, Robotics Foundation Models, Agentic RL (PhD) Responsibilities* Develop agentic RL algorithms for post-training WAMs and VLAs using large, heterogeneous robot datasets.* Investigate agentic RSI, reward learning, value estimation, and policy optimization for generative action models, including approaches that use learned world models to support policy improvement.* Address challenges in learning from mixed-quality experience, including distribution shift, sparse rewards, and long-horizon credit assignment.* Build efficient training and data pipelines, and study how policy performance scales with dataset size, model capacity, and compute.