SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Atoms is building Physical AI—autonomous robots for real-world industries including mining, food production, and transport. The company integrates hardware, software, AI, and operations to deploy intelligent systems at scale in challenging physical environments.
As a Senior Robotics Controls Engineer, you will develop and maintain core control systems for autonomous haul trucks operating in mining environments. You'll own the design, implementation, and tuning of control algorithms for 200+ ton vehicles, including localization, path following, longitudinal control, and steering systems.
Key responsibilities:
- Design and implement control algorithms for autonomous vehicle systems
- Build localization and state estimation pipelines that fuse multiple sensor modalities (GPS/RTK, IMUs, CAN interfaces)
- Develop lateral and longitudinal control and navigation systems
- Analyze system performance through simulation and field testing
- Debug control issues using logged data and identify root causes
- Collaborate with perception, planning, and hardware teams to integrate control systems
- Write production-quality Python code for reliable, efficient operation
- Periodic travel to customer sites (up to 15%) and schedule flexibility during deployments
Required qualifications:
- BS/MS/PhD in Robotics, Mechanical Engineering, Aerospace Engineering, Electrical Engineering, or related field
- 7+ years of professional software development experience
- Strong foundation in classical control theory (PID, lead/lag compensation, stability analysis)
- Experience with state estimation (Kalman filters, EKF/UKF)
- Proficiency in Python and NumPy/SciPy
- Understanding of vehicle dynamics and kinematics
- Experience deploying localization and controls algorithms on real-world systems
Desired experience includes Model Predictive Control (MPC), path following algorithms (Stanley, Pure Pursuit), signal processing, system identification, heavy equipment/off-highway vehicles, CAN bus interfaces, ROS, and modern ML techniques for controls.
Technical environment: Python (primary), C++ (optimization-critical paths), NumPy, SciPy, NVIDIA Jetson hardware, field testing on haul trucks, log replay, and simulation.
