I am a Senior Software Engineer at Dexory with a PhD in Computer Vision and Machine Learning from the University of East Anglia. I specialise in building scalable, high-performance perception systems that power inventory warehouse automation and digital twins through the fusion of cameras, LiDAR, and 3D point clouds. My expertise spans neural network architecture, visual navigation, and geospatial understanding, with strong proficiency in Python, PyTorch, and TensorFlow. Throughout my career, I have consistently delivered robust models for semantic segmentation and object detection, ranging from geospatial analysis to developing computer vision solutions that assist autonomous navigation of visually impaired individuals.