Industrial · Autonomous mining trucks
| Title | Stage | AI score |
|---|---|---|
| Planning Engineer Planning Engineer role at Caterpillar focused on path and behavior planning for autonomous mining vehicles in unstructured environments. Responsibilities include task-level route planning, trajectory and speed planning considering vehicle dynamics and terrain, and perception-based behavior planning. Requires strong C++/Python skills, familiarity with Linux and ROS/ROS2, and knowledge of ML/DL/RL applications in planning. Experience in autonomous driving planning and decision-making is essential, with mining/construction scene experience being a plus. | Agent | 7 |
| Perception deployment engineer This role focuses on deploying, optimizing, and validating deep learning perception models on embedded platforms for autonomous mining vehicles. It involves using tools like TensorRT and CUDA for inference acceleration, performance analysis, and system-level engineering in a Linux Embedded environment. Collaboration with algorithm, fusion, system, and hardware teams is crucial for integration and evolution, as well as problem-solving during full-process debugging and testing. |
| Serve |
| 7 |
| Autonomy Simulation Engineer The role is responsible for the design and development of the simulation architecture for mine autonomous driving systems, covering backend control system simulation, autonomous vehicle simulation, subsystem simulation, and simulation and testing of autonomous driving algorithms. The goal is to achieve efficient verification and iteration in a virtual environment, reduce on-site testing risks, and improve development efficiency. Key responsibilities include building a simulation platform for multi-vehicle, multi-scenario collaborative testing, simulating backend logic, developing vehicle dynamics and sensor models, simulating core algorithms like path planning and obstacle avoidance, and developing test scenarios. Experience with simulation systems (CARLA/AirSim/Isaac Sim), ROS, C++, Python, and multi-agent simulation frameworks is required. Familiarity with machine learning/deep learning, especially data-driven or reinforcement learning methods in simulation, is a plus. | Agent | 7 |