Bridging Biology, Physics & Technology — from the atomic scale of organometallic chemistry to production-grade computer vision systems.
With a PhD in Pathophysiology and a Masters in Industrial Processes, my work defies conventional disciplinary boundaries. I approach every problem as a system — whether it's understanding disease mechanisms, synthesising novel molecules, or architecting production-scale software platforms.
My research trajectory spans organometallic chemistry at UNSW Sydney, AI-powered clinical diagnostics, cancer pharmacology, and the invention of ConeRod — a physics-based computer vision algorithm inspired by biological photoreceptors.
I bring the same rigour that produced breakthrough results in JACS to every domain I enter — from bioprocesses to embedded vision systems, from cosmological theory to platform architecture.
Organometallic synthesis, cationic transition metal-alkane complexes, conductor polymer design, and photovoltaic cell construction. Published in JACS.
AI-powered clinical diagnostics, cancer pharmacology, multivariate biomedical analysis, and disease mechanism modelling at the molecular and systems level.
Physics-based vision algorithms that simulate biological photoreception. Inventor of ConeRod — certifiable without machine learning under European safety standards.
Full-stack platform design from infrastructure to mobile applications, delivering complete production systems independently across backend, APIs, vision pipelines, and iOS apps.
Original theoretical work on dark matter as spacetime ripples, cyclical universe models, and the application of physical principles to computational challenges.
Fungal biotechnology for biodiesel production, industrial bioprocesses, and sustainable chemistry. Applied biological systems to energy and materials challenges.
66 nodes across 8 domain clusters. Proximity to the centre is governed by connection density — highly connected concepts orbit close, deep specialisations radiate outward.
A novel physics-based detection algorithm that simulates the biological function of cone and rod photoreceptor cells in the human retina — without machine learning.
Unlike neural network approaches, ConeRod operates deterministically — making it certifiable under EN 54 European fire and smoke safety standards. Machines can now see the way biology evolved to see light.
ConeRod separates luminance and chrominance channels, applies biologically-inspired sensitivity curves, and produces certifiable detection outputs from standard CCTV hardware.
Open to research collaborations, technology licensing discussions (ConeRod), consulting engagements, and senior platform architecture roles — particularly in the UK and Europe.