Research Scientist Intern: Agentic RL for Robotic Models

Meta

Menlo Park (CA)

On-site

USD 55,000 - 83,000

Full time

13 days ago

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Meta Reality Labs Research in Menlo Park is seeking a Research Scientist Intern to develop scalable offline reinforcement learning methods for post-training these models. Interns will conduct both fundamental and applied research to advance foundation models for robotics, focusing on post-training.

You will collaborate with researchers and engineers to build and evaluate model capabilities, design experiments, and publish results at leading ML and robotics venues.

Qualifications

  • PhD candidate or degree in CS/ML/Robotics.
  • Experience in RL including policy optimization and offline/off-policy learning.
  • Experience implementing and training deep learning models with Python and PyTorch.
  • Ability to design controlled experiments and analyze results.
  • Collaborative cross-group communication.

Responsibilities

  • Develop agentic RL algorithms for post-training WAMs and VLAs using large robot datasets.
  • Investigate reward learning, value estimation, and policy optimization for generative action models.
  • Address learning from mixed-quality experience, distribution shift, sparse rewards and long-horizon credit.
  • Build training and data pipelines; study how policy performance scales with data and compute.
  • Design experiments and benchmarks to evaluate policy generalization across tasks and environments.
  • Collaborate with researchers and engineers to evaluate policies in simulation and on real robots.
  • Communicate research findings and publish results at leading ML and robotics venues.

Skills

Reinforcement learning
Python
PyTorch
Offline RL
Robotics
Experiment design
Distributed training
Mathematical foundations

Education

PhD in CS/ML/Robotics

Tools

PyTorch
Python
Linux

Job description

Meta Reality Labs Research in Menlo Park is seeking a Research Scientist Intern to develop scalable offline reinforcement learning methods for post-training these models. Interns will conduct both fundamental and applied research to advance foundation models for robotics, focusing on post-training.

You will collaborate with researchers and engineers to build and evaluate model capabilities, design experiments, and publish results at leading ML and robotics venues.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Research Scientist Intern: Robotics Foundation Models & RL
Research Scientist Intern: Robotics Foundation Models & RL

Meta • Menlo Park (CA)

On-site
USD 41,000 - 69,000
Research Scientist Intern - Robotics Foundation Models - Agentic RL
Research Scientist Intern - Robotics Foundation Models - Agentic RL

Meta • Menlo Park (CA)

On-site
USD 41,000 - 69,000
Research Scientist Intern, Robotics Foundation Models, Agentic RL (PhD)
Research Scientist Intern, Robotics Foundation Models, Agentic RL (PhD)

Meta • Menlo Park (CA)

On-site
USD 55,000 - 83,000
Research Scientist Intern - Humanoid Control & Dexterous Manipulation
Research Scientist Intern - Humanoid Control & Dexterous Manipulation

Meta • Redmond (WA)

On-site
USD 30,000 - 47,000
ML Research Intern: Foundation Models & RL
ML Research Intern: Foundation Models & RL

Modal Labs • San Francisco (CA)

On-site
USD 60,000 - 90,000
Mentorship by senior researchers
Research publication opportunities
PhD internship stipend
Robotics AI Research Scientist Intern
Robotics AI Research Scientist Intern

Meta • Burlingame (CA)

On-site
USD 85,000 - 141,000
Remote RL Research Intern — Agentic AI & LLMs
Remote RL Research Intern — Agentic AI & LLMs

Centific Global Solutions, Inc. • United States

Remote
USD 48,216 - 61,992
Competitive stipend
Mentorship from researchers
Access to modern GPU infrastructure
PhD ML Research Intern — RL & Foundation Models
PhD ML Research Intern — RL & Foundation Models

Modal Labs • New York (NY)

On-site
USD 34,440 - 82,656
Research Scientist Intern, Multimodal AI & Robotics
Research Scientist Intern, Multimodal AI & Robotics

Meta • Sunnyvale (CA)

On-site
USD 85,000 - 141,000
Benefits
Paid Research Intern — Robot Learning & Manipulation
Paid Research Intern — Robot Learning & Manipulation

Proception Inc. • Mountain View (CA)

Hybrid
USD 41,000 - 55,000