Senior Manipulation Engineer (Imitation Learning), Discovery

Anduril Industries

Quick summary

Work type
On-site
Location
Costa Mesa, CA · Washington, DC
Salary
$166,000–$220,000 / yr
Posted
today

Market check

Salary context

Below market

How this pay compares to similar roles

Similar $213k
This role $193k
$156k most similar roles pay here $263k

This role pays less than 69% of similar roles. Most pay $177,762–$247,531 — the shaded band above. At the midpoint, this role pays about $193k versus about $213k for comparable roles.

Based on 240 similar postings.

Employer

About Anduril Industries

Anduril Industries is a defense technology company that builds advanced hardware and software systems for national security, including autonomous drones, surveillance systems, and the Lattice AI command platform.

Anduril Industries currently has 1882 open roles on FindRole.

Listed pay typically runs $146,000–$194,000 across 1696 roles with salary data.

Most-posted roles

View all roles at Anduril Industries

At a glance

TL;DR · Senior Manipulation Engineer (Imitation Learning), Discovery

As a Senior Manipulation Engineer at Discovery, you will join a team dedicated to advancing robotic manipulation in unstructured environments. Your primary responsibilities include designing and deploying visuomotor policies for robots using imitation learning techniques such as behavior cloning and diffusion policy models. You will manage the teleoperation data collection pipeline, develop task-specific skill policies, and collaborate with locomotion and perception engineers to integrate these skills into a comprehensive control system. The role requires expertise in Python, PyTorch, and deep learning frameworks like LeRobot and ACT, along with hands-on experience in robot manipulation and visuomotor control. This position addresses the challenge of enabling robots to perform complex tasks autonomously in real-world settings.

What you'll do

  • Design and train visuomotor manipulation policies using behavior cloning and imitation learning.
  • Build and maintain teleoperation systems for real-robot demonstration data collection.
  • Develop task-specific skill policies for grasping, tool use, bimanual manipulation, and assembly operations.
  • Own the full pipeline from data collection to model training, evaluation, and deployment on embedded compute.
  • Collaborate with locomotion engineers to integrate manipulation skills into a whole-body control architecture.

What we're looking for

  • 3+ years of experience developing and deploying robot learning systems on real robots.
  • Strong background in robot manipulation, visuomotor control, behavior cloning, and imitation learning.
  • 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.

More like this

Similar roles

Senior Machine Learning Engineer, RL / Locomotion

Anduril Industries

Costa Mesa, CA today $220,000$336,000
Python PyTorch RSL_RL Stable_Baselines rl_games Isaac_Gym MuJoCo PyBullet PPO SAC GPU-parallelized_simulation sim-to-real_transfer reinforcement_learning NVIDIA_Isaac_Lab Omniverse

Senior Machine Learning Engineer - Robotics

Johnson & Johnson

Remote (Us328 Ca Santa Clara - 5490 Great America Pkwy, US) 8 days ago $125,000$201,250
Python PyTorch TensorFlow C++ MuJoCo Isaac Sim Git CI/CD Robot Kinematics Robot Dynamics Sensing and Control Simulation Platforms Deep Learning Frameworks Vision-Language-Action Models(VLAs) Agile Development Processes
Remote

Senior Robotics Research Scientist

Nvidia

Seattle, WA 146 days ago $192,000$304,750
Python ROS2 PyTorch JAX CUDA Warp Isaac_Sim Isaac_Lab MuJoCo C++ CVPR ICRA IROS NeurIPS ICML ICLR ECCV Simulation Real-to-Sim Bimanual_Manipulation Mobile_Manipulation Vision-Language-Action_Models