Back to roles

Meta

Research Scientist Intern, Physics-Grounded Multimodal Robot Learning

Posted Today

Internship

Redmond, Washington

On-site

Smart Summary

Plan and execute research to advance robotics in policy learning, sensor fusion, and real-time state estimation. Collaborate with researchers to develop and integrate perception methods and evaluate performance on robotic systems.

Must Have Skills for ATS

robot learning

sensor fusion

real-time state estimation

machine learning

Python

PyTorch

reinforcement learning

behavior cloning

physics simulation

Job Description

Meta Reality Labs is seeking a Research Scientist Intern with expertise in robot learning, sensor fusion, and real-time state estimation. The ideal candidate will have experience training and adapting robot policies, with a strong background in machine learning, real time state estimation, reconstruction and robotics. As an intern, you will explore how learned policies and multimodal sensing can improve robotic control and dexterous manipulation. This includes learning object state, physical properties and interaction dynamics, either implicitly within policies or through explicit estimation, to support robust, adaptive robot behavior. Our internships are twelve (12) to twenty-four (24) weeks long, with various start dates throughout the year.Responsibilities
  • Plan and execute research to advance robotics in the areas of policy learning, sensor fusion, and real-time state estimation.
  • Train new robot policies and fine-tune and apply pretrained models, including vision-language-action (VLA) models/WAM, and policies learned through reinforcement learning (RL) or behavior cloning (BC), for real-time robotic applications.
  • Develop and integrate perception, sensor fusion, and state-estimation methods to support robotic control and manipulation.
  • Collaborate with researchers and engineers to prototype hardware and software solutions, run experiments, and evaluate performance on robotic systems.
  • Work with leading researchers to develop publishable research for top-tier journals and international conferences.
Minimum Qualifications
  • Currently has, or is in the process of obtaining, a PhD in Robotics, Machine Learning, Computer Vision, Computer Science, or a related technical field
  • Research experience in robot learning, perception, state estimation, or control, with a strong foundation in machine learning
  • Proficiency in Python and experience with a deep-learning framework such as PyTorch
  • Research skills involving defining problems, exploring solutions, and analyzing and presenting results
  • Must obtain work authorization in the country of employment at the time of hire and maintain ongoing work authorization during employment
Preferred Qualifications
  • Demonstrated research ownership and the ability to conduct cutting-edge research with minimal supervision, along with a proven track record of research contributions through publications at venues such as CoRL, RSS, ICRA, IROS, NeurIPS, ICML, CVPR, ICCV or related conferences and journals
  • Experience training new robot policies and fine-tuning pretrained models, including VLA or WAM models and policies trained using reinforcement learning (RL) or behavior cloning (BC)
  • Experience with multimodal sensor fusion, real-time state estimation, tracking, or robotic sensing for dexterous manipulation
  • Experience deploying learned policies on robotic systems, including real-time inference and closed-loop control
  • Experience with physics simulation engines for robotics (such as MuJoCo and SuperDex), sim-to-real transfer, or system identification
  • Experience working and communicating cross-functionally in a research or engineering team
  • Intent to return to the degree program after the internship and availability for at least sixteen (16) consecutive weeks
$7,650/month to $12,667/month + benefits

Meta's mission is to build the future of human connection and the technology that makes it possible. Our technologies help people connect, find communities, and grow businesses. When Facebook launched in 2004, it changed the way people connect. Apps like Messenger, Instagram and WhatsApp further empowered billions around the world. Now, Meta is moving beyond 2D screens toward immersive and intelligent experiences like virtual reality, wearables and AI to help build the next evolution in social technology. To help create a safe and respectful online space, we encourage constructive conversations on this page. Please note the following: • Start with an open mind. Whether you agree or disagree, engage with empathy. • Comments violating our Community Standards will be removed or hidden. Please treat everybody with respect. • Keep it constructive. Use your interactions here to learn about and grow your understanding of others. • Our moderators are here to uphold these guidelines for the benefit of everyone, every day. • If you are seeking support for issues related to your Facebook account, please reference our Help Center (https://www.facebook.com/help) or Help Community (https://www.facebook.com/help/community). For a full listing of our jobs, visit https://www.metacareers.com

You're Early

Posted24h3d1w2w+

Posted 6 hours ago. Apply today while the pile is still small.

LAND THE INTERVIEW

See your odds before you apply.

Your Score

69%

Top Applicants

80%+

  • Your gaps for this role

    What to address in your resume before you apply
  • Get a Warm Intro

    Find alumni, current interns & recruiters at this company
  • Interview Guide

    Comprehensive questions and interview strategy for this role
  • Be the first next time

    Roles like this sent to you before LinkedIn or Handshake