Robotic Algorithm Engineer

Job Description We are building a next-generation humanoid robot platform with high-bandwidth torque-controlled joints and full-body actuation. Our short- to mid-term goal is to achieve robust and reliable locomotion in indoor service and industrial environments.As a Robotics Algorithm Engineer focused on Locomotion, you will work across simulation, learning-based control, state estimation, and real-robot deployment. This is a highly hands-on role requiring both strong implementation skills and the ability to debug complex real-world robotic behaviors.We are looking for engineers who not only implement algorithms, but also develop their own technical insights and adapt quickly in a rapidly evolving robotics landscape.ResponsibilitiesLocomotion & Learning-Based ControlDevelop and deploy RL-based locomotion policies for humanoid robotsDesign training pipelines including domain randomization and sim-to-real transferImprove policy robustness for indoor service and industrial use casesAnalyze and debug failure modes from both simulation and real-world testingFull-Body Control & ModelingWork on whole-body control frameworks integrating learned policiesUnderstand and leverage robot dynamics models for stability and contact reasoningContribute to state estimation using IMU, joint encoders, and contact sensingSimulation & ToolingBuild and maintain locomotion simulation environments (Mujoco / Isaac)Design training environments and reward shaping strategiesAnalyze the simulation-real gap and iterate on mitigation strategiesReal Robot DeploymentDeploy policies to hardware with torque-controlled, high-bandwidth actuatorsPerform real-robot tuning, debugging, and performance optimizationWork closely with firmware, motor control, and hardware teamsQualificationsMust Have3+ years of experience in robotics, control, or locomotion-related rolesStrong C++ and Python programming skillsExperience applying reinforcement learning to robotics control problemsExperience deploying algorithms on real robots (not simulation-only)Solid understanding of rigid body dynamics and feedback controlFamiliarity with state estimation for legged robotsExperience working in Linux environmentsNice to HaveExperience with humanoid or legged robotsWhole-Body Control or MPC exposureMujoco / Isaac Gym / Isaac Sim experienceExperience addressing sim-to-real transfer challengesFamiliarity with Pinocchio, CasADi, or similar toolsCUDA or large-scale RL training experienceROS2 experienceWork ModeOn-site requiredUp to 10% of travel