Robotics Autonomy Engineer – Locomotion

Job description

Job responsibilities

• Architect and implement scalable reinforcement learning (RL) pipelines optimized for locomotion and manipulation.
• Integrate physics-based simulation environments (Isaac Gym, Isaac Lab, MuJoCo) with custom training workflows.
• Develop reward functions, policy architectures, and domain randomization strategies that close the sim-to-real gap.
• Create agile, robust locomotion behaviors for quadruped and humanoid platforms, and validate them on real hardware.
• Solve real-world challenges in balance, contact-rich dynamics, high-DOF coordination, and terrain variability.
• Drive iterative testing across terrain variability and unstructured environments.
• Build scalable training environments using GPU-accelerated simulators.
• Automate evaluation across domain-randomized scenarios and domain adaptation protocols.
• Maintain simulation infrastructure that enables rapid prototyping, validation, and reproducibility.
• Work closely with systems engineers, perception experts, and embedded teams to close the loop between learning and execution.
• Incorporate real-world telemetry and field data to continuously improve model generalization.
• Lead deployment workflows from experiment through lab testing to field robot validation.

Job requirements

• Master’s degree or higher in Robotics, Computer Science, Engineering, or related field (PhD strongly preferred).
• Deep expertise in reinforcement learning for continuous control.
• 2+ years of experience developing and deploying locomotion policies on real robotic systems (preferred).
• Hands-on experience with legged robot platforms (quadrupeds, bipedal systems, or exoskeletons).
• Proficiency with simulation tools such as Isaac Gym, Isaac Lab, MuJoCo, or PyBullet.
• Strong command of sim-to-real transfer — domain randomization, system identification, adaptive methods, and a track record of bridging the gap successfully.
• Solid understanding of contact dynamics, control theory, and kinematics.
• Strong Python and/or C++ development skills in Linux-based development environments.
• Familiarity with machine learning frameworks (PyTorch, TensorFlow).
• A passion for building things that move in the real world.
• 3+ years of experience in an industry or startup robotics setting.
• Experience deploying neural network controllers on resource-constrained robotic platforms (real-time inference, onboard compute).
• Publications or open-source contributions in locomotion, RL, or control.
• Familiarity with ROS/ROS2 or custom middleware for real-time control.
• Background in manipulation, loco-manipulation, or whole-body coordination.
• Experience debugging sim-to-real issues at scale.
• Contributions to reinforcement learning libraries or simulation platforms.
• Prior work on multi-agent learning or terrain-adaptive control systems.