Senior Manipulation Engineer (Imitation Learning), Discovery

Anduril Industries is a defense technology company with a mission to transform U.S. and allied military capabilities with advanced technology. By bringing the expertise, technology, and business model of the 21st century’s most innovative companies to the defense industry, Anduril is changing how military systems are designed, built and sold. Anduril’s family of systems is powered by Lattice OS, an AI‑powered operating system that turns thousands of data streams into a realtime, 3D command and control center. As the world enters an era of strategic competition, Anduril is committed to bringing cutting‑edge autonomy, AI, computer vision, sensor fusion, and networking technology to the military in months, not years.

ABOUT THE TEAM

The Discovery team at Anduril is at the forefront of incubating and maturing high‑potential, software‑defined, AI‑native offerings that meet the toughest, newest challenges across hardware, software, space, and cyber domains. We’re the architects of mission autonomy and mesh networking, delivering scalable hardware solutions that meet some of the most urgent national security needs. By working hand‑in‑hand with elite teams in Perception, AI, Motion Planning, Hardware, Test Engineering, Space, Networking, and Vehicle hardware, we craft cutting‑edge, end‑to‑end systems that redefine mission success.

ABOUT THE JOB

We are seeking a Senior Manipulation Engineer to develop learned manipulation policies for robotic platforms operating in unstructured environments. You will build the skill policies that enable our systems to grasp objects, operate tools, turn valves, open doors, and perform assembly tasks — trained from human demonstration data and deployed on real hardware. You will own the full loop: teleoperation data collection, policy training, real‑world evaluation, and iteration.

WHAT YOU’LL DO

Design, train, evaluate, and deploy visuomotor manipulation policies using behavior cloning and imitation learning (ACT, Diffusion Policy, VLA models) Build and maintain the teleoperation and data collection pipeline for real‑robot demonstration capture 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 Work with perception engineers to design vision inputs for skill policies

REQUIRED QUALIFICATIONS

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

PREFERRED QUALIFICATIONS

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 Salary range: $166,000—$220,000 USD.

BENEFITS

Anduril offers a comprehensive benefits package available at little to no cost to employees, supporting health, recovery, and career growth. Equity grants are included in most full‑time offers, and a competitive set of health, dental, vision, disability, and retirement benefits are also provided. #J-18808-Ljbffr TryApplyNow