Outcome 02

Turn AI into production software

Most AI projects die in the gap between a convincing demo and a system you can depend on. I’ve spent years on the production side of that gap.

The symptoms

  • You have a promising prototype but no path to production.
  • There’s no honest way to tell whether the model is actually good.
  • Data is scattered and the pipeline breaks quietly.
  • Nobody’s sure what it will cost — or whether it’s safe to ship.

What I do

  1. 01Design the data platform underneath the model — streaming, storage, and recovery that don’t lose data.
  2. 02Build LLM and MCP systems that put live business data safely in front of the people who need it.
  3. 03Put evaluation and A/B testing in place so model quality is measured, not assumed.
  4. 04Own the path to production: deployment pipelines, monitoring, and cost.

Proof

  • Media · AdTech2017–23

    Co-founder & CTO — ML personalisation

    Designed end-to-end model deployment and continuous A/B testing, serving real-time recommendations to millions of users for major broadcasters — 10,000+ requests per second at a 19 ms p99, under contractual SLAs.

    20%+ lift in pageviews

  • E-commerce2025–26

    AI/ML platform engineer — e-commerce group

    Built a ClickHouse lakehouse fed by real-time streams from 13+ webshops, and an MCP server giving non-technical staff LLM-powered analytics over live data through Claude.

    Live analytics for non-technical users

  • Media2015–17

    Lead data engineer — broadcaster

    Architected a next-generation analytics and ML platform combining batch and real-time pipelines for recommendations and audience insight.

    50+ TB processed per day

And underneath
  • LLMs · MCP
  • ClickHouse · Kafka
  • PySpark · MLlib
  • MLOps · A/B testing

Next step

Let’s talk about where your engineering is heading.

A 30-minute call, no pitch. Tell me what’s slowing you down and I’ll tell you honestly whether I can help.

Prefer a bounded first step? Start with the two-week review