Consulting

I work with external partners where deep technical judgement is needed about computation in its physical form: digital electronics, computer architecture, arithmetic, memory, machine learning, accelerators, and the route from code or mathematical intention to efficient implementation.

This work has taken several forms, including personal consultancy, independent technical advice in patent litigation, early-stage review of technical ideas, and research sponsorship.

For non-confidential enquiries, please email me with the question, the decision you are trying to make, and the relevant timeframe.

What I Bring

A useful engagement can either take the form of assessing an existing proposal or of bringing my own research to bear on a problem by identifying representations, arithmetics, architectures, abstractions, or proofs that change what is possible.

In the right industrial or startup context, this can mean helping shape the technical direction of a new system, finding a sharper computational formulation, or connecting a practical constraint to ideas from hardware-aware machine learning, arithmetic, high-level synthesis, and structural models of computation.

Questions I Can Help With

  • Is this accelerator, arithmetic, or hardware-aware machine learning idea technically plausible?
  • What are the real limits on latency, throughput, area, energy, precision, or accuracy?
  • How does a claimed invention sit relative to prior art in digital electronics, computer architecture, memory systems, or numerical computation?
  • Which parts of a workload are inherent, and which are incidental artefacts of a particular implementation?
  • Can a software, mathematical, or machine learning workload be mapped effectively to FPGA or custom hardware?
  • Is there a different representation, arithmetic, architecture, or abstraction that would make this problem easier or more valuable?
  • Which ideas from my research could become a practical technical advantage in this setting?
  • What kind of evidence would change a technical, legal, investment, or product decision?

Modes of Engagement

Independent technical advice and patent litigation

I have acted as an independent technical expert in patent litigation cases with major international law firms, across digital electronics, computer architecture, memory technology, and numerical computation. This work draws on historical context, prior art, and first-principles analysis of how systems are represented and built.

Technical review and due diligence

I help industry partners, investors, and technical leaders assess the potential and limitations of new computational ideas. Typical questions include whether a proposed hardware architecture is credible, what the hidden bottlenecks are, what the relevant comparison points should be, and whether a claimed advantage is likely to survive contact with implementation.

Startup and deep-tech collaboration

I am open to conversations with founders and deep-tech builders where hardware, machine learning, arithmetic, compilation, or code-to-silicon ideas could become a serious technical advantage. For more detail, see Startup collaboration.

Research sponsorship

I work with industry partners who are interested in the deep structure of computation, especially where mathematical insight, hardware-aware design, and machine learning meet. I collaborate with industry partners because I believe research ideas sharpen when exposed to real constraints, and industry-facing work can strengthen the academic community as well as the partner organisation.

Areas of Expertise

Hardware-aware machine learning

  • Ultra-low-precision and quantised models
  • Hardware-native neural networks, including LUT-based and Boolean approaches
  • Co-design of algorithms and architectures
  • Theoretical analysis of error, robustness, and structure

FPGA and custom-accelerator design

  • FPGA-based machine learning inference and training
  • Data-path optimisation for arithmetic-heavy workloads
  • Resource/performance trade-offs involving latency, throughput, area, and energy
  • Parallelism, pipelining, and domain-specific architectures

Arithmetic, precision, and correctness

  • Novel computer arithmetics and precision models
  • Digit-serial arithmetics
  • Equality-saturation and e-graph rewriting for correctness and optimisation
  • Formal reasoning about numerical behaviour

Code-to-hardware translation

  • High-level synthesis
  • Mapping software kernels to reconfigurable or custom hardware
  • Identifying architecture parameters from program structure
  • Understanding when code structure helps or obstructs hardware implementation

Digital electronics and architecture

  • Context and prior art in digital electronics, numerical computation, memory systems, computer architecture, and accelerators
  • First-principles analysis of computational systems and their implementation constraints
  • Independent assessment of technical claims, system behaviour, and architectural trade-offs

First Contact

If you would like to discuss consultancy, technical advice, startup collaboration, or research sponsorship, please contact me by email with a short non-confidential summary of the question, the decision you need to make, and the relevant timeframe.