My experience spans software engineering, deep learning, firmware, and hardware development. I enjoy the full development cycle, from conceptualisation and hardware design to software implementation and data analysis. I'm fascinated by explainable AI (XAI) and mechanistic interpretability in medical applications. In healthcare, AI systems must be transparent and interpretable - doctors and patients need to understand why an AI makes certain decisions, not just what those decisions are. This is crucial for building trust in medical AI systems and ensuring they can be safely deployed in clinical settings. I'm lucky enough to have had internships as an Embedded Engineer, SWE, and an upcoming ML internship – all in the bioengineering/science space (haven't sold out to finance yet).

In addition to your standard engineering mathsy modules, I've got skills in:

• programming (C++, Python, Kotlin)
• deep learning with PyTorch (specialised uni modules, Andrej Karpathy's excellent 'Zero to Hero' series building and training GPT from scratch, projects for Image Segmentation, Registration and Reconstruction)
• solid+fluid mechanics through uni modules (inc. biomechanics, CFD, FEA)
• hardware development experience (projects, uni modules)