Research Engineer Robotics (systems)

Meta Meta · Big Tech · Redmond, WA +1

Meta's Reality Labs Research is seeking a Staff Research Engineer to lead the end-to-end technical architecture for dexterous robotic manipulation systems. This role involves integrating perception, planning, and control, deploying learned control policies (including imitation learning and reinforcement learning), and building infrastructure for data capture and processing. The engineer will optimize system performance, set technical direction, and mentor other engineers, bridging the gap between research and production in robotics.

What you'd actually do

  1. Architect & Own Real-Time Robotic Systems: Design and maintain real-time dexterous manipulation pipelines that integrate perception, planning, and control across multiple robotic platforms.
  2. Lead Data Capture & Retargeting Infrastructure: Architect motion capture integration, novel hardware prototypes, and human demonstration data collection systems.
  3. Drive ML-Systems Integration: Deploy and iterate on learned control policies (imitation learning, MPC, reinforcement learning) within full robotic systems.
  4. Optimize Performance & System Reliability: Own runtime performance, debug complex system behaviors across the stack, and develop interactive demos and benchmarks that demonstrate research progress
  5. Set Technical Direction: Identify and drive cross-cutting technical improvements.

Skills

Required

  • Bachelor's degree in Computer Science, Computer Engineering, Robotics, or related technical field (or equivalent practical experience)
  • 5+ years of experience in robotics engineering, including hands-on work with robotic platforms in industry or academic research settings
  • Demonstrated experience with machine learning systems in a robotics context (e.g., learned control policies, perception models, or ML-driven planning)
  • Full-stack systems engineering experience designing, building, and maintaining large-scale software-hardware systems
  • Track record of driving complex, ambiguous technical projects from conception through delivery with minimal direction
  • Experience communicating technical decisions and system designs to cross-functional stakeholders across research and engineering functions (e.g., design documents, technical reviews, project proposals)
  • Experience building and operating systems that bridge research exploration and reliable deployment
  • Deep familiarity with robotics frameworks (e.g., ROS/ROS2) and real-time robotic control systems

Nice to have

  • Master's or Ph.D. in Robotics, Computer Science, Electrical Engineering, or related field
  • Background in computer vision, imitation learning, reinforcement learning, model-predictive control, or sim-to-real transfer
  • Demonstrated ongoing AI skill development (e.g., prompt/context engineering, agent orchestration) and staying current with emerging AI technologies
  • Experience in dexterous manipulation, learned robotic policy deployment, or control theory applied to real hardware
  • Experience designing data capture protocols and building high-quality ML datasets at scale
  • History of mentoring engineers and influencing technical direction beyond your immediate team
  • Experience adhering to and implementing responsible, ethical AI practices (e.g., risk assessment, bias mitigation, quality and accuracy reviews)
  • Demonstrated ability to integrate AI tools to optimize/redesign workflows and drive measurable impact (e.g., efficiency gains, quality improvements)

What the JD emphasized

  • end-to-end technical architecture
  • deployment of learned control policies
  • integration of robotic embodiments
  • real-time robotic systems
  • ML-Systems Integration
  • learned control policies
  • reinforcement learning
  • sim-to-real transfer
  • robotics frameworks
  • real-time robotic control systems

Other signals

  • end-to-end technical architecture
  • deployment of learned control policies
  • integration of robotic embodiments
  • real-time robotic systems
  • ML-Systems Integration
  • learned control policies
  • reinforcement learning
  • sim-to-real transfer
  • robotics frameworks
  • real-time robotic control systems