Work
Selected engagements
Described by sector, region and year, newest first. We do not name clients, and we do not publish work that a client would prefer we did not — which means this page is a sample rather than a record.
-
A 25W sensor for drone detection, identification and direction finding
A deployable sensor that finds drones by their radio emissions, identifies them where they broadcast and classifies them where they do not, and takes a bearing on a target that is actively trying not to hold still — with everything, inference included, running on the node inside 25 watts.
RF signal processing · Edge AI · Embedded systems · Sensor fusion
-
A passive micro-Doppler sensor for fused situational awareness
Prototype of a sensor that classifies airborne targets from micro-Doppler signatures without transmitting — PCB design, component selection under supply constraints, firmware, and the software that fuses its output with other sensors.
PCB design · Firmware · Signal processing · Sensor fusion
-
Retrofit autonomy for existing crewed vessels
Design and prototype of an autonomy package fitted to vessels already in service — custom interface hardware, edge compute, protocol bridging and a communications path that degrades predictably offshore.
PCB design · Edge compute · Marine protocols · Communications
-
Feasibility assessment for downstream refinery waste conversion
A regional refinery held a waste stream it treated as a disposal cost. We modelled the thermal and catalytic pathways for converting it into saleable by-products and assessed each against regulatory and commercial constraints.
Process modelling · Techno-economic analysis · Regulatory assessment
-
Reducing signal-processing latency in a news-driven trading system
A proprietary trading firm needed millisecond-level reaction to high-frequency news feeds. We replaced the tokenisation stage of its sentiment pipeline with cache-resident probabilistic filters, cutting signal-processing latency by an order of magnitude.
Low-latency systems · Signal processing · Performance engineering
-
A digital twin for thermochemical conversion research
An industrial R&D facility was constrained by the cost and duration of physical experiments. We coupled a kinetics-driven simulation engine to live sensor data, giving the team a validated model to explore reaction space before committing to a run.
Simulation · Machine learning · Instrumentation
-
Resolving flow-pressure instability across a regional water network
Pump activation cycles, sensor lag and pressure regulation were interacting in ways the utility's SCADA data could not explain. We built an augmentable variable model with virtual sensors to close the gap between what the network did and what its instrumentation reported.
Process control · Sensor modelling · Industrial data
-
A real-time risk engine for a regional energy trading desk
The desk was managing exposure on end-of-day positions in a market that moved intraday. We built a multi-factor risk system fed by live market data, giving continuous assessment and a defensible basis for portfolio optimisation.
Risk systems · Market data · Quantitative modelling
-
Predictive signal models for volatile asset trading
A European fund needed signal models that held up in the conditions where its returns were actually determined. We built an ensemble across market sentiment, technical and alternative data, evaluated specifically under high volatility.
Quantitative research · Machine learning · Trading systems
-
Verifiable carbon yield measurement across forestry assets
Carbon sequestration across a forestry portfolio was being estimated on survey cycles measured in years. We designed a system pairing aerial LiDAR with geospatial analytics to value carbon yield continuously and verifiably.
Geospatial analytics · Asset instrumentation · Verification systems
-
Automating first-pass screening in a venture dealflow pipeline
A growth-stage venture firm was losing partner time to unqualified dealflow. We deployed an assisted screening layer against its CRM and portfolio analytics, shortening review cycles without removing partner judgement from the decision.
Process automation · Applied AI · Systems integration
-
Structuring a securitised instrument from trade receivables
A European FinTech held cashflows from trade receivables and no route to institutional capital. We designed the risk-scoring basis and asset structure that turned those cashflows into a fixed-income product.
Structured finance · Risk modelling · Corporate structuring
Full case studies are available on request.
Enquiries
Start with the problem
If you are weighing a system decision that is difficult to reverse, we are glad to look at it with you. An initial conversation carries no obligation and no fee.