Perception Deployment Engineer

Caterpillar Caterpillar · Industrial · Wuxi, Jiangsu

This role focuses on deploying and optimizing deep learning perception models on embedded NVIDIA platforms (Jetson/Orin) for autonomous mining vehicles. Responsibilities include using tools like TensorRT, CUDA, and ONNX Runtime for inference acceleration, performance analysis, and system-level engineering in a Linux Embedded environment. Collaboration with algorithm, fusion, system, and hardware teams is key for integration and evolution.

What you'd actually do

  1. 负责深度学习感知模型在车端嵌入式平台的部署、优化与验证
  2. 在 Jetson / Orin 等 NVIDIA 嵌入式平台完成模型落地
  3. 使用 TensorRT、CUDA、cuDNN、ONNX Runtime 等工具进行端侧推理加速
  4. 针对延迟、吞吐量、内存占用、功耗等指标进行性能分析与优化
  5. 在 Linux Embedded 环境下开展系统级工程工作,包括:驱动与系统配置协作,交叉编译,系统服务调试,Docker / DeepStream / ROS2 等运行环境构建与维护

Skills

Required

  • C++
  • Python
  • Linux Embedded
  • deep learning model deployment
  • embedded platform experience
  • problem decomposition
  • system integration debugging

Nice to have

  • multi-threading
  • CUDA optimization
  • object detection
  • object segmentation
  • Jetson/Orin experience
  • ROS2
  • DeepStream
  • system stability
  • maintainability
  • scalability

What the JD emphasized

  • 嵌入式平台实际落地经验
  • 具备良好的问题拆解能力
  • 能够在系统联调阶段独立推进问题定位与解决

Other signals

  • deployment
  • optimization
  • embedded platforms
  • inference