Projects
A selection of work across machine learning, deep learning, computer vision, and generative AI, from academic research to applied business problems.
My Master's thesis explored automated identification of medicinal plant species from leaf imagery. I built an image-classification pipeline using convolutional neural networks and transfer learning from pre-trained backbones, adapting them to a specialised botanical dataset to reach reliable accuracy on a fine-grained recognition task.
Design and delivery of generative-AI capabilities: from retrieval-augmented generation over internal knowledge to LLM-assisted workflows that reduce manual effort. Focused on grounding model output in trusted data, evaluating quality, and shipping something dependable rather than a demo.
A postgraduate project boosting sales efficiency for an EdTech firm: feature engineering over operational data, model building to identify the drivers of performance, and turning the results into recommendations the business could act on.
A postgraduate computer-vision project building gesture recognition for smart TVs. It classifies hand gestures from video sequences, combining spatial feature extraction with temporal modelling to interpret motion over time.