Dexmate is at the forefront of developing advanced robotic systems that solve real-world challenges. We're building next-generation robots designed to work alongside humans, operate in human environments, and help address growing labor shortages.
Position Overview
We are seeking talented Control Engineers to join our dynamic team and lead the development of state-of-the-art control and state estimation algorithms for our robot platform.
Key Responsibilities
Develop and implement state estimation, sensor fusion, planning, control algorithms that enable fast, dynamic and safe robot motion
Collaborate with cross-functional teams including embedded system, perception, hardware, AI
Optimize control performance across multiple domains including stability, safety, precision, and energy efficiency
Design and conduct experiments to validate control algorithms both in simulation and on hardware
Analyze system performance data to identify failure modes and improvement opportunities
Document technical approaches, implementation details, and experimental results
Requirements
Master's or PhD in Robotics, Controls, Mechanical Engineering, or related technical field
4+ years of professional experience developing control systems for dynamic robots
Strong expertise in control theory including nonlinear control, model predictive control, and optimal control
Experience with state estimation techniques such as Kalman filters, particle filters, and factor graphs
Proficiency in C++, Python, Rust for real-time robotics applications
Strong understanding of robot kinematics, dynamics, and mathematical modeling
Experience working with sensor integration including IMUs, encoders, force/torque sensors
Proven track record of implementing and testing control algorithms on physical robotic systems
Excellent problem-solving skills and ability to debug complex system interactions
Preferred Qualifications
Experience with highly dynamic control systems such as bipedal, quadruped, or humanoid robots
Knowledge of reinforcement learning or other machine learning approaches for control
Experience with whole-body control and contact dynamics for legged systems
Experience with real-time computing and optimization
Background in trajectory optimization and motion planning
Familiarity with ROS, simulation environments (e.g., Drake, Isaac Sim, SAPIEN, MuJoCo, PyBullet)
Track record of publications in top-tier robotics conferences/journals