Controls and Robot Learning Engineer

About the role

Join the team bringing advanced autonomy to the built world. At Bedrock, we're deploying autonomous systems on heavy construction equipment across the country, improving safety on job sites and accelerating schedules on critical infrastructure projects. You'll work alongside construction veterans and world-class engineers to solve physical-world problems that simulations can't touch.

Responsibilities

• Onboard Control: Develop control laws for the base vehicle and automated arms, utilizing techniques such as MPC, Reinforcement Learning, linear and non-linear control, computed torque, vehicle dynamics, and impedance control.
• System Identification and Modeling: Build models that capture the state and control input propagation of complex construction robots like excavators. This involves a deep understanding of the direct and inverse geometry of robot arms (4 to 7 DOFs), vehicle dynamics, and overall system calibration.

Requirements

• 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

Skills

• 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

Our roles are often flexible. If you don't fit all the criteria, or are in another location (especially one where we have an office like SF or NY) please apply anyway!