Robotics Manipulation & Motion Planning Engineer

AICAM Mondovi Site (Cuneo) is looking for a

Robotics Manipulation & Motion Planning Engineer

About AICAM

AICAM ( ) is Raicam's robotics division, focused on developing and industrializing service robots for real hospitality environments.

About the role

We are looking for a Manipulation & Motion Planning Engineer to develop the robot's physical interaction capabilities, from perception-driven planning to execution on real hardware. You will work on closing the loop between planning, control, and real-world behavior, enabling the robot to perform complex manipulation tasks in dynamic, unstructured environments. You will operate at the intersection of motion planning, manipulation, system integration, and real robot deployment.

Responsibilities

• Design and implement motion planning pipelines that produce collision-free, dynamically feasible trajectories, integrating mechanical and task constraints, handling perception uncertainty, and adapting to real-world execution limits.
• Develop grasp strategies for the objects our robots encounter in service environments, including rigid and deformable items from imperfect perception.
• Implement force-aware and impedance-based behaviors for contact phases such as placing, sliding, and handovers.
• Coordinate planning across dual arms and mobile base as a unified redundant system, enabling loco-manipulation in spaces shared with humans and furniture.
• Interface the manipulation stack with the perception pipeline and the real-time control stack (e.g. running over EtherCAT).
• Build high-fidelity simulation models of the robot for training manipulation algorithms and rapid testing. Validate on real hardware and drive iterative cycles of refinement and redeployment.

Requirements

• Strong background in robotic manipulation, with hands-on experience on real hardware.
• Deep understanding of robot kinematics (FK/IK), rigid-body dynamics, collision checking, and trajectory generation.
• Hands-on experience with MoveIt 2 or equivalent production motion planning frameworks.
• Proficiency in C++, Python, ROS 2.
• Proven ability to debug and tune robotic systems in real-world conditions, dealing with sensor noise, latency, and mechanical limitations.

Nice to have

Experience in any of the following is a plus. We do not expect one person to cover all of them:

• Experience with advanced planning tools (cuRobo, Drake, OMPL, TrajOpt) and/or GPU-accelerated simulation environments (Isaac Lab, ManiSkill, MuJoCo MJX).
• Impedance, admittance, or hybrid force-position control implemented on real hardware with real-time communication protocols.
• Familiarity with learning-based manipulation (grasp regression from point clouds, Diffusion Policy, ACT, VLA-class models) or reinforcement learning + sim-to-real transfer.
• Whole-body control for mobile manipulation systems.
• Experience with soft robotics, including soft grippers, for safe and adaptive interaction with objects and humans.

What we are looking for

• Engineers who bridge theory and real-world execution and are comfortable both reading research papers and diagnosing hardware issues on the bench.
• A focus on robustness and recoverability over ideal-case performance.
• Strong ownership mindset on complex subsystems, with the initiative to push back when something is not working.
• Genuine interest in solving open manipulation problems rather than applying standard pipelines.

We are an Equal Opportunity Employer, applications are welcome from all genders and without any distinction