Gradientrobotics

Controls Engineer

San Francisco. Posted 3 months ago

The role

The Controls Engineer will own motion from command to actuator. This includes modeling physical systems, designing controllers for sub-millimeter precision, and selecting motion and sensing hardware.

What you will do

  • Model and identify axes and arms using physical principles and measurement
  • Diagnose and resolve field issues including resonances, instability, non-linearities, joint compliance, latency, sensor noise, and dynamic variability
  • Design and tune control loops including current, velocity, and position cascades, inverse-dynamics feedforward, notch and loop-shaping filters, and force/impedance control
  • Select and source motion and sensing hardware and fieldbus modes
  • Commission commercial drives and specify custom drive/loop architectures
  • Develop test procedures to verify performance and iterate from failed tests to tuned revisions

Required qualifications

  • 3+ years' experience in controls engineering on physical electromechanical systems with control loops tuned on real hardware
  • Strong control theory fundamentals: frequency-domain analysis, stability margins, loop shaping, discrete-time effects, and sound judgment for controller selection
  • Demonstrated system identification skills: measured FRFs, model fitting, and controller design using those models
  • Experience with serial robot arms: forward and inverse kinematics, rigid-body dynamics, friction compensation
  • Expertise in debugging nonlinearity and bandwidth-limiting problems and explaining their root causes
  • Fluency in Python for analysis
  • Ability to write and review real-time control code in C, C++, or Rust

Nice to have

  • Experience with force/impedance control or other contact-rich robotic manipulation
  • Knowledge of precision motion technologies including ball screws, linear motors, direct drive, and air bearings
  • Familiarity with EtherCAT or CANopen, CSP/CST modes, and real-time Linux environments

About the company

Gradient builds the autonomous robots that make datacenter buildout possible. They move fast and build full-stack systems.