We are building the control intelligence that enables our humanoid robot 4NE-1 to move, balance, manipulate, and interact safely in complex real-world environments. We are looking for a Locomotion & Whole-Body Control Engineer to join our Humanoid Controls team in Zurich and develop the core algorithms that power dynamic locomotion and whole-body behavior on the physical robot.
This role spans the key layers of the humanoid control stack, from trajectory optimization and model predictive control (MPC) for motion generation to whole-body control (WBC) for executing those motions reliably on real hardware at high control frequencies.
You will work on contact-rich humanoid dynamics, real-time optimization, and robust control deployment, collaborating closely with state estimation, simulation, low-level controls, hardware, and AI teams to enable stable and adaptable humanoid behavior in practical applications.
Your mission & challenges
- Develop whole-body motion generation and control algorithms for the 4NE-1 humanoid, including locomotion, balancing, contact transitions, and loco-manipulation tasks.
- Design and implement trajectory optimization and MPC pipelines for humanoid motion generation, considering robot state, contact schedules, ground reaction forces, centroidal momentum, and joint trajectories.
- Build and maintain QP-based whole-body control and task-space inverse dynamics frameworks to execute planned motions on the physical robot at frequencies up to 1 kHz.
- Develop and improve dynamic models of the humanoid system, including floating-base rigid-body dynamics, forward and inverse kinematics, Jacobians, and full-body dynamics computation.
- Formulate and implement kinematic, dynamic, contact, friction, torque, stability, and joint-limit constraints across planning and control layers.
- Improve solver performance, numerical robustness, and real-time reliability of optimization pipelines deployed on hardware.
- Deploy, tune, and validate locomotion and whole-body control algorithms on physical humanoid robots, including debugging hardware-specific effects, contact models, and control performance.
- Develop high-performance C++ software for real-time control systems and build Python-based tooling for analysis, testing, and prototyping.
- Collaborate closely with engineers across controls, hardware, simulation, perception, AI, and systems teams to deliver integrated humanoid capabilities.
What we can look forward to
- MSc or PhD in Robotics, Controls, Mechanical Engineering, Electrical Engineering, Computer Science, or a related field.
- 4+ years of hands-on experience developing locomotion, MPC, trajectory optimization, and/or whole-body control for physical robotic systems.
- Strong foundation in floating-base articulated rigid-body dynamics and contact modeling.
- Deep understanding of centroidal dynamics, SRBD, LIPM, or related reduced-order models used in humanoid locomotion.
- Strong background in optimal control, constrained optimization, and model predictive control.
- Experience developing and deploying whole-body control frameworks such as TSID, inverse dynamics, or hierarchical QP controllers on real robotic hardware.
- Hands-on experience deploying real-time control systems operating at 500 Hz–1 kHz.
- Strong C++ skills and good Python proficiency for tooling, diagnostics, and prototyping.
- Practical understanding of real-world robotic control challenges including actuator limits, state-estimation uncertainty, communication latency, contact uncertainty, and model mismatch.
- Strong collaboration and communication skills with the ability to work effectively across multidisciplinary robotics teams.
Nice to Have
- Direct experience working on humanoid robots or other floating-base high-DOF robotic systems.
- Familiarity with Pinocchio, MuJoCo, Crocoddyl, OCS2, TSID, IPOPT, CasADi, or similar robotics and optimization frameworks.
- Experience with hierarchical QP, operational space control, task prioritization, and contact force optimization.
- Experience with dynamic walking, balance recovery, push recovery, and multi-contact locomotion.
- Experience with manipulation-aware locomotion and whole-body coordination of arms, torso, and lower body.
- Experience with torque-controlled robots and high-bandwidth electric actuation.
- Publications at RSS, ICRA, IROS, or CoRL related to locomotion, whole-body control, optimization, or humanoid robotics.
