osama zaman

I’m a junior AI/ML engineer who builds computer vision systems and deep learning models, then turns them into end-to-end ML pipelines. I aim to keep models practical—optimizing training, data augmentation, and deployment constraints so results hold up outside of experiments.

I’ve also contributed to published research in GAN-based medical image synthesis (IEREK/AURAK 2026, Scopus-indexed proceedings). My work reflects a mindset of rigorous evaluation, careful dataset handling, and iteration toward measurable improvements.

In projects, I’ve developed real-time detection and multi-object tracking with YOLOv8 and ByteTrack, and built a Kinect v2 + OpenCV projector system for depth mapping and size/distance estimation running on Raspberry Pi. I’m actively developing my skills in LLMs and Generative AI, and I’m open to internships and junior roles where mentorship and real-world deployment are prioritized.