Unit: Human Centered AI, Data & Software
Group: Trustworthy AI
Social links: LinkedIn / ResearchGate
Languages: Portuguese, Spanish, French, English
Research Engineer working in AI benchmarking, evaluation metrics and computer vision. My work focuses on developing and analyzing deep learning models for complex and noisy environments, with experience ranging from medical imaging, space and defense applications, including context-aware metrics, explainability, data augmentation strategies, and the implementation of AI workflows within benchmarking platforms.
Contribute to the defense project on AI benchmarking, metrics implementation, workflow development and adversarial data augmentation Participate in the geospatial project, focusing on specification review, deployment tasks and upcoming benchmarking activities. Implement explainable and context-aware metrics (scene complexity, depth, augmentation conditions, etc.). Assist in the deployment and operation of the AI Benchmarking Platform. Design and evaluate deep learning models for detection, segmentation, and robustness analysis.
