• Computer Vision • Vision Language Models • 3D Vision • AI Agents
Deep Learning and Computer Vision Engineer with 5+ years of experience developing AI solutions in computer vision, deep learning, robotics, and LLM-powered systems. Experienced in building end-to-end applications involving object detection, segmentation, OCR, tracking, medical imaging, and retrieval-augmented generation using PyTorch, TensorFlow, OpenCV, and YOLO. Conducted research in 3D vision and neural rendering, focusing on 3D Gaussian Splatting for sparse-view novel view synthesis and translating cutting-edge research into practical, production-ready AI systems.
End-to-end AI systems from research to deployment
MS Thesis — NUST. Improved sparse-view reconstruction using DepthAnything-V2 geometric priors and composite loss functions.
Thesis · 2025Comprehensive review of 3DGS techniques, benchmarking state-of-the-art methods for novel view synthesis and scene reconstruction.
Review Paper · 2025AI-based flight data analysis with interpretable models for anomaly detection and predictive maintenance.
Conference Paper · 2024Whether you're building a startup or looking for a Computer Vision Engineer, I'd love to help turn your ideas into production-ready AI systems.