Open position

Senior Software Engineer (Motion Planning)

Onsite San Jose, CA Senior Full-time $200,000 – $250,000

We are seeking a Senior Software Engineer to build the manipulation planning and control libraries in AMP. The work covers collision-free motion generation, trajectory optimization, and the execution layer that turns a planned motion into repeatable movement on real arms.

The target applications are palletization, bin picking, and machine tending on KUKA arms and mobile manipulators, under cycle time and reliability requirements.

You will work in the core robotics manipulation team alongside controls and perception engineers.

What you’ll do

  • Build and own manipulation planning capability in AMP: collision-free planning, trajectory optimization, and time parameterization.
  • Implement and tune planners for the target applications, with cycle time as a first-class requirement.
  • Build the collision environment representation from perception output and static scene models.
  • Implement Cartesian and constrained motion planning for approach, grasp, and place phases.
  • Handle the mobile manipulation cases: planning with base placement, redundancy resolution, and whole-body motion.
  • Build the execution layer that monitors trajectory tracking and reacts to deviation and contact.
  • Define the interface between perception, planning, and control, and keep it clean as the system grows.
  • Diagnose planning failures from field data and turn them into regression cases.

Job requirements

Experience

  • 4 to 8 or more years of professional engineering experience, with at least 2 years in motion planning or manipulation.
  • Experience deploying manipulation planning on physical arms in a production or field setting.
  • Experience meeting a cycle time requirement, not only a feasibility requirement.

Education

  • Master's degree or higher in Robotics, Computer Science, Mechanical Engineering, Electrical Engineering, or a closely related technical field.
  • Equivalent industry experience with demonstrated manipulation depth may be considered.

Core technical background

  • Strong grounding in motion planning: sampling-based methods, optimization-based methods, and their respective failure modes.
  • Solid kinematics and dynamics: forward and inverse kinematics, redundancy resolution, singularity handling, and Jacobian methods.
  • Experience with trajectory optimization and time-optimal path parameterization.
  • Experience with collision checking and distance queries, including performance characteristics.
  • Hands-on experience with MoveIt, OMPL, TrajOpt, Drake, or comparable frameworks.
  • Strong C++, plus Python. Hands-on experience with ROS or ROS 2.

Systems mindset

  • Ability to trade planner optimality against solve time and explain the choice.
  • Comfortable reasoning about real-time constraints and control loop interaction.
  • Debugs manipulation failures on hardware.

Collaboration

  • Able to work effectively with remote teams across multiple time zones.
  • Comfortable working closely with perception, controls, and safety engineers.

Nice to have

  • Experience with KUKA arms, KRL, or the KUKA controller interfaces.
  • Experience with force control, impedance control, or contact-rich manipulation.
  • Experience with mobile manipulation and whole-body control.
  • Experience with learned or hybrid planning approaches.
  • Prior open-source contributions to MoveIt or the ROS manipulation ecosystem.