About Asiacruit

At Asiacruit, we connect top talent with forward-thinking organizations across industries. Our mission is to help businesses grow through smart, strategic, and people-focused solutions. We support companies by providing high-quality talent for local and global markets.

Position Overview

We are seeking a Locomotion & Controls Engineer to develop and validate locomotion and motion control systems for advanced legged robots.

In this role, you will design and train gait controllers that enable robots to walk, trot, climb stairs, and navigate challenging terrain, including mud, rocks, and uneven surfaces. You will work across robotics simulation, control algorithms, state estimation, and sim-to-real deployment to help translate locomotion research into reliable performance on physical robots.

Key Responsibilities

• Develop and maintain simulation environments with randomized rough terrain for locomotion training and evaluation.

• Design, implement, and optimize gait controllers for walking, trotting, stair climbing, crawling, and other locomotion tasks.

• Apply reinforcement learning, model predictive control (MPC), or a combination of approaches to develop stable and adaptive locomotion policies.

• Transfer locomotion controllers from simulation to physical robots and tune their performance during real-world testing.

• Develop state estimation methods for estimating robot body pose and velocity using IMU, joint sensors, and other available sensor inputs.

• Evaluate locomotion stability, terrain adaptability, disturbance recovery, and overall control performance.

• Define actuator and leg performance requirements to support the selection of suitable off-the-shelf components and suppliers.

• Collaborate with mechanical, embedded systems, perception, and AI engineers to integrate and validate the complete robotic system.

Qualifications

• Master's degree or PhD in Mechanical Engineering, Electrical Engineering, Aerospace Engineering, Robotics, Control Systems, or a related field. A strong research background in legged locomotion is highly valued.

• 5–8 years of relevant experience in legged robotics, locomotion control, robot dynamics, or closely related research and engineering.

• Strong understanding of rigid-body dynamics, robot kinematics, and control theory.

• Hands-on experience developing locomotion controllers using reinforcement learning, including PPO, model predictive control (MPC), or related control approaches.

• Practical experience with at least one robotics physics simulator, such as NVIDIA Isaac Sim/Isaac Lab, MuJoCo, PyBullet, Gazebo, or RaiSim.

• Experience deploying and validating controllers on physical robot hardware, not only in simulation.

• Proficiency in C++ and Python.

• Ability to analyze robot stability, state estimation, and locomotion performance in real-world conditions.

Preferred Qualifications

• Experience with commercial quadruped platforms such as Unitree, ANYmal, Boston Dynamics Spot, or Deep Robotics, including their SDKs.

• Familiarity with open-source legged robotics frameworks such as legged_gym, OCS2, Pinocchio, Drake, or Crocoddyl.

• Research publications at robotics conferences such as ICRA, IROS, CoRL, RSS, or Humanoids.

• Experience with Kalman filters, terrain-aware foothold planning, and sensor fusion.

• Familiarity with PyTorch, GPU-based reinforcement learning training, and domain randomization.

• Experience with humanoid robots, exoskeletons, or other legged robotic platforms.

Why Join?

• Work on challenging locomotion problems involving dynamic balance, terrain traversal, and adaptive robot movement.

• Apply advanced control theory and reinforcement learning to physical robotic systems.

• Contribute to the development of robotics capabilities from simulation through real-world testing.

• Collaborate with a multidisciplinary engineering team working on advanced robotic platforms.