I help companies building hardware and AI products avoid costly technical mistakes - designing edge intelligence systems that work in production and scale for the next five years.
Experience across world-class engineering organisations
I translate complex engineering choices into practical execution paths - so leadership can move faster, reduce risk, and avoid six- to seven-figure mistakes in hardware and AI development.
Design ML systems that run reliably on constrained devices in real-world conditions - from model selection to deployment and lifecycle planning.
Connect sensors, devices, and cloud into coherent, secure, and maintainable systems that hold up at scale instead of becoming technical debt.
Intelligent robot software and behaviours - from perception and control to navigation - engineered for next-generation products that perform outside the lab.
See around corners before technical debt forms. Choose the right platforms, models, and deployment paths with confidence and a clear scaling plan.
Identify the expensive failure modes early - deployability, reliability, and maintainability - so you don't pay for avoidable rework later.
Level up engineering teams turning ideas into executable systems - drawing on years mentoring with DIET and the University of Bristol.
Real-world breakdowns of complex edge AI and IoT decisions - what was at stake, what path was chosen, and how risk was reduced.
Applying robotics, automation, and AI to high-precision, low-volume manufacturing in watchmaking, jewelry, and related industries.
Read case study
How edge AI enables robots to sense, decide, and act reliably in real-world environments through low-latency, hybrid physical AI architectures.
Read case study
OpenClaw now controls my rover via ROS 2, turning high-level goals into real hardware actions with on-device perception and speech.
Read case studyPeer-reviewed contributions across robotics, edge AI, and intelligent systems.
Journal of Medical Robotics Research · 2021
A pilot study that trains a deep neural network to map a surgeon's wrist, hand and finger movements to microsurgical tool pose during mock cardiac ...
View publication
International Conference on Computer and Drone Applications (IConDA) · 2017
A low-cost system for autonomous indoor navigation and landing of an AR.Drone 2.0 using its front- and bottom-facing cameras with an ArUco marker. ...
View publication
International Conference on Advanced Robotics (ICAR) · 2019
An active-perception method (NBV-SPE) for locating stationary sound sources with a single motion-capable acoustic sensor. It combines an Extended K...
View publicationWatch my latest thinking on edge AI, robotics, and building systems that scale.
Need architectural clarity before a major edge AI or IoT investment? Let's get the technical strategy right so you don't pay for avoidable mistakes later.