車電Algorithm Deployment and Performance Optimization Engineer(內湖) - TWPR01485

1. Port, integrate, and deploy algorithms to specific embedded platform such as NVIDIA, Qualcomm and etc.
2. Collaborate with AI/ML teams to optimize AI models on embedded platform.
3. Propose and implement optimization strategies to improve algorithm efficiency.
4. Analyze algorithm performance and resource utilization on embedded platforms.
5. Validate AI model input and output correctness and consistency during inference.
6. Design, develop, and maintain APIs, tooling, and reusable integration components and tools.
7. Integrate AI inference frameworks such as TensorRT, ONNX Runtime, and similar technologies.