Senior Manipulation Engineer (imitation Learning), Discovery

Anduril Anduril · Defense · Costa Mesa, CA · AFS : Discovery Engineering : Discovery Engineering

Senior Manipulation Engineer focused on developing and deploying learned manipulation policies for robotic platforms using imitation learning techniques. The role involves the full pipeline from data collection to model training and real-world evaluation on embedded systems.

What you'd actually do

  1. Design, train, evaluate, and deploy visuomotor manipulation policies using behavior cloning and imitation learning (ACT, Diffusion Policy, VLA models)
  2. Build and maintain the teleoperation and data collection pipeline for real-robot demonstration capture
  3. Develop task-specific skill policies for grasping, tool use, bimanual manipulation, and assembly operations
  4. Own the full pipeline from data collection to model training, evaluation, and deployment on embedded compute
  5. Collaborate with locomotion engineers to integrate manipulation skills into a whole-body control architecture

Skills

Required

  • 3+ years of experience developing and deploying robot learning systems on real robots
  • Strong background in robot manipulation and visuomotor control
  • Experience with behavior cloning, imitation learning, or related methods
  • Hands-on experience with teleoperation systems and demonstration data collection
  • Proficiency in Python, PyTorch, and modern deep learning frameworks
  • Experience with LeRobot, ACT, Diffusion Policy, or similar IL frameworks
  • Eligible to obtain and maintain a U.S. security clearance

Nice to have

  • Experience deploying learned manipulation in production or commercial robotic systems
  • Experience with dexterous hands or multi-fingered grippers
  • Prior work on bimanual manipulation
  • Publications in manipulation, robot learning, or embodied AI

What the JD emphasized

  • deploy learned manipulation in production or commercial robotic systems

Other signals

  • robot learning
  • imitation learning
  • manipulation policies
  • real-world deployment