Computer Vision Engineer

We are looking for a computer vision / machine learning engineer to help build and improve an object-detection model for image and video analysis. The project involves working with an existing or partially prepared image dataset, training or fine-tuning a YOLO-based model, evaluating detection accuracy, reducing false positives/false negatives, and preparing the model for practical use in a production or edge-device environment. The ideal developer should be comfortable with Python, PyTorch, OpenCV, YOLO, image preprocessing, model evaluation, and inference optimization. Scope of work: Review the current image/video dataset and labelling quality Recommend improvements to the annotation structure if needed Train or fine-tune a YOLO/object-detection model Evaluate model performance using clear metrics Improve accuracy, false positives, missed detections, and inference speed Prepare the model for deployment through an API, ONNX export, or lightweight inference setup Document the training process, assumptions, results, and next recommended steps This is not a simple AI API integration or chatbot project. We need someone who can work directly with computer vision models, datasets, evaluation, and deployment readiness. Please apply with examples of previous work involving object detection, OCR, image classification, video analytics, edge AI, or production ML model deployment.