Job Description
Responsibilities
- Design and deploy real-time computer vision and AI inference pipelines on embedded ARM and FPGA-based platforms.
- Implement inference engines using C++ (primary) and Python.
- Optimize AI models for latency, memory, and power constraints.
- Convert and deploy models using ONNX, TensorFlow SavedModel, and TensorFlow Lite.
- Integrate streaming and device communication using MQTT, TCP, and UDP.
- Develop deployment workflows using Docker and embedded CI pipelines.
Required Skills
- Strong C++ for embedded systems
- Python for AI pipelines and tooling
- ARM-based embedded Linux experience
- FPGA integration knowledge
- OpenCV, ONNX Runtime, TensorFlow/TFLite
#J-18808-Ljbffr