Perception Deployment Engineer
Core
Deploy, optimize, and validate deep learning perception models on vehicle-side embedded platforms for autonomous mining operations.
Role type
Embedded systems engineer specializing in perception model deployment
Builds
Real-time perception inference pipelines on NVIDIA embedded hardware for autonomous vehicles
Domain
Autonomous mining vehicles / Embedded AI / Robotics
Deliverable
production ML models
Required skills
C++, Python, NVIDIA Jetson/Orin deployment, TensorRT, CUDA, cuDNN, ONNX Runtime, Linux embedded systems, Docker, ROS2, DeepStream, LiDAR point cloud processing
Preferred skills
Multi-threading, performance optimization, object detection/segmentation understanding, system stability focus
Technologies
Jetson, Orin, TensorRT, CUDA, cuDNN, ONNX Runtime, Linux, Docker, DeepStream, ROS2
Responsibilities
Optimize model latency, throughput, memory usage, and power consumption; Collaborate on driver and system configuration; Cross-compile and debug system services; Integrate perception modules with vehicle systems; Troubleshoot bugs in point cloud algorithm chains
Seniority
Mid-level, hands-on IC
