Controls and Robot Learning Engineer

The role

You will develop onboard and offboard autonomy system components. You will create models for onboard controls and analyze, evaluate, and simulate the system dynamics of complex construction robots.

What you will do

• Develop control laws for the base vehicle and automated arms using MPC, Reinforcement Learning, linear and non linear control, computed torque, vehicle dynamics, and impedance control.
• Build models that capture the state and control input propagation of complex construction robots like excavators.
• Apply deep understanding of direct and inverse geometry of robot arms (4 to 7 DOFs), vehicle dynamics, and overall system calibration.

Required qualifications

• 5+ years of professional engineering or research experience in control and real-time embedded systems
• MSc or PhD in Computer Science or Robotics
• Deep understanding of reinforcement learning, imitation learning, and optimization for dynamic systems
• Strong programming skills (C++/Rust, Python)
• Strong data analysis skills
• Experience with safety-critical systems

Nice to have

• Experience with machine learning training pipelines, especially reinforcement learning (RL) using learned or simulated plant models
• Practical application of RL or model predictive control (MPC) for control algorithms in production autonomy environments
• Experience working with pose estimation systems
• Experience with controlling and modeling hydraulic systems

About the company

Bedrock retrofits heavy equipment like excavators to provide autonomy for construction. The team includes veterans from Waymo, Segment, and Uber Freight.