Description
The role designs, trains, and deploys production computer vision and deep learning systems for real-time image and video analysis. Responsibilities include developing object-detection and attribute-extraction models, building low-latency video ingestion and processing pipelines, implementing LPR, OCR, and multi-object tracking, optimizing inference on cloud and edge platforms, and managing datasets and automated retraining. The position requires at least three years of production computer vision and deep learning experience, expertise in modern detection architectures, Python and deep learning frameworks, video stream processing, and familiarity with quantization, ONNX, and TensorRT.
