Senior Embedded Vision Engineer

About the Role

You will lead the development of an edge-AI camera platform. The journey starts with prototyping and model training on NVIDIA Jetson, then moves to production hardware built on Raspberry Pi 4/5 with the Hailo-8L accelerator, or on a custom Jetson-based board.

Key Responsibilities

• Bring up and tune CSI camera modules (IMX708, IMX477, IMX219 class), including the ISP, libcamera and GStreamer pipelines.
• Train, fine-tune and validate YOLO object detection models using datasets from real deployment cameras.
• Build depth estimation (monocular and stereo) and integrate it with detection.
• Deploy models on Jetson with TensorRT, and on Raspberry Pi with Hailo-8L through ONNX export, Hailo Dataflow Compiler (INT8 calibration), and HailoRT.
• Run feasibility studies comparing Jetson versus RPi + Hailo, covering performance, cost, thermal, and supply-chain tradeoffs.
• Lead schematic and PCB design for custom boards, including MIPI-CSI, PCIe, and power design.
• Define test plans for accuracy, latency, FPS, and thermal behavior to verify outputs before production release.
• Document the design process and mentor junior engineers.