Senior Motion Planning Engineer

A fast-growing robotics company is developing autonomous robotic systems for demanding, real-world industrial environments. Its engineering team works across robotics, AI, perception and autonomy to develop reliable, high-performance systems for deployment in production settings.

The company is looking for an experienced Senior Robotics Engineer to help advance robotic motion planning and performance, with significant ownership over technical direction and the opportunity to make a measurable impact on real-world robotic systems.

We are looking for a Senior Robotics Engineer to lead the next phase of motion-performance improvement for a robotic manipulator. You will be the technical lead for motion planning and trajectory generation, owning how planned motion is converted into fast, smooth, dynamically feasible trajectories under real hardware constraints.

Your focus will be reducing cycle time while maintaining safety and payload stability, using strong fundamentals in kinematics, dynamics, constrained optimisation and hardware-backed performance validation.

This is a senior individual-contributor role. You will set technical direction for motion planning, own complex trajectory-optimisation problems and mentor other engineers, working closely with the wider autonomy team.

• Own trajectory generation and time parameterisation, converting planned paths into time-optimal, dynamically feasible trajectories that minimise cycle time while respecting velocity, acceleration, jerk and torque limits of the robot arm and payload.
• Drive improvements in motion performance through advanced time parameterisation, optimisation-based motion techniques, including optimal control and QP/NLP, and payload-aware planning.
• Ensure smooth, jerk-limited motion that maintains payload stability and hardware safety.
• Robustly handle near-singularity and joint-limit edge cases without stalls or unsafe motion.

• Own geometric path planning for a high-degree-of-freedom manipulator operating in cluttered and partially occluded environments.
• Evaluate and evolve the planning architecture and toolchain, making decisions around whether to build, adopt or extend existing frameworks such as Move It, OMPL, CHOMP and Traj Opt.
• Integrate perception outputs, including environmental frames, object poses and occupancy information, into the planning scene.
• Reason about collision objects and constraints to ensure safe, reliable movement through complex environments.

• Define motion-performance metrics, benchmark alternative approaches and validate improvements in both simulation and on real hardware.
• Use physics-based and kinematic simulation to develop and de-risk changes before deployment.

• Set technical direction for motion planning and drive longer-term improvements in cycle time and reliability.
• Mentor junior and mid-level engineers, raising standards across motion planning, testing and system reliability.
• Collaborate across autonomy, perception, controls and robot software to deliver motion that is both fast and reliable across diverse operating conditions.

• 5+ years of professional experience in motion planning, trajectory optimisation or manipulator control.
• Experience deploying robotics solutions on production systems or real hardware.
• A track record of owning motion performance and delivering measurable improvements end to end.

• Bachelor's or Master's degree in Robotics, Computer Science, Mechanical Engineering, Electrical Engineering or a related field, or equivalent industry experience.

• Strong grounding in classical trajectory-generation and time-parameterisation methods, such as TOTG/TOPP-RA, Ruckig and S-curve profiles, with the ability to derive, adapt and implement them in production systems.
• Deep understanding of manipulator kinematics and dynamics, including forward and inverse kinematics, collision checking, velocity, acceleration, jerk and torque constraints, and singularity and joint-limit handling for 6- or 7-DOF arms.
• Experience with optimisation-based motion, including optimal control and QP/NLP-based trajectory optimisation.
• Strong proficiency in modern C++, Python and ROS 1 or ROS 2.
• Experience validating cycle-time and reliability improvements on real hardware, supported by simulation.

• Strong problem-solving and data-driven decision-making skills, with the…