Ehsan Nazari
ML Researcher & CV Engineer | Visual Recognition · Representation Learning
At Pacefactory, I build and deploy visual recognition systems for industrial environments — object detection, keypoint detection, and segmentation from raw camera feeds. I leverage foundation models (SAM, CLIP, Grounding DINO) for annotation and zero-shot classification, and design lightweight pipelines for edge deployment.
I hold a Master’s in Applied AI from the University of Ottawa (GPA: 10/10, Vector Scholarship recipient), where my research focused on GANs and adversarial attacks on face recognition systems under Professors Branco and Jourdan.
On my own time, I research visual understanding — how deep networks learn, represent, and generate visual content. Recent project. I also write about object detection internals on Medium.