SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Bedrock Robotics is deploying autonomous systems on heavy construction equipment across the country. The company has raised $350M in two years and achieved the first fully autonomous excavator deployments in construction, with a team that includes veterans from Waymo, Segment, and Uber Freight.
As a Controls and Robot Learning Engineer, you will develop crucial components of the onboard and offboard autonomy system for autonomous construction machines. Your work will span two primary areas:
Onboard Control: You'll develop control laws for the base vehicle and automated arms using techniques such as model predictive control (MPC), reinforcement learning, linear and non-linear control, computed torque, vehicle dynamics, and impedance control. This requires deep understanding of how to command complex, 100,000-pound construction robots in real-world conditions.
System Identification and Modeling: You'll build models that capture state and control input propagation of complex construction robots like excavators. This involves understanding direct and inverse geometry of robot arms (4-7 degrees of freedom), vehicle dynamics, and overall system calibration.
You'll work alongside construction veterans and world-class engineers solving physical-world problems that simulations cannot fully address. The role requires translating algorithms into steel-toed-boot reality—deploying AI systems that improve safety on job sites and accelerate schedules on critical infrastructure projects.
Required qualifications include 5+ years of professional engineering or research experience in control and real-time embedded systems, an MSc or PhD in Computer Science or Robotics, deep understanding of reinforcement learning and imitation learning for dynamic systems, strong programming skills in C++/Rust and Python, strong data analysis capabilities, and experience with safety-critical systems.
Standing-out qualifications include experience with machine learning training pipelines (especially reinforcement learning using learned or simulated plant models), practical application of RL or MPC for control algorithms in production autonomy environments, experience with pose estimation systems, and experience controlling and modeling hydraulic systems.
