AI Model Evaluator (Self-directed)
Image
As an AI Model Evaluator for raxen.ai & Guardx.ai, I evaluated and labelled outputs from computer vision and surveillance models. I applied structured criteria to assess model behaviors and annotated training datasets to improve model precision. Consistent annotation was maintained across large volumes of image and video data. • Evaluated accuracy, false positives, and edge cases for surveillance AI models
• Categorized model behavior across different input conditions
• Iteratively annotated datasets for AI training pipeline improvements
• Maintained standards for labeling consistency and quality
As an AI Model Evaluator for raxen.ai & Guardx.ai, I evaluated and labelled outputs from computer vision and surveillance models. I applied structured criteria to assess model behaviors and annotated training datasets to improve model precision. Consistent annotation was maintained across large volumes of image and video data. • Evaluated accuracy, false positives, and edge cases for surveillance AI models • Categorized model behavior across different input conditions • Iteratively annotated datasets for AI training pipeline improvements • Maintained standards for labeling consistency and quality
2022 - Present