May meetup: Building valuable products in a probabilistic world

Leeds Data Science Meetup's May 2026 session brings two practitioners to The Elbow Room on Call Lane for back-to-back talks on building AI systems that actually work in production.

John Carney, Principal Consultant at PDFTA and co-founder of PyDataMCR, opens with a talk titled Building Valuable Deterministic Products in a Probabilistic World. The premise is straightforward: almost everything in software has historically been deterministic, but LLMs change that. Carney argues that building with or around LLMs requires a different set of techniques and principles, and he'll share what those look like in practice. He brings experience across data engineering, machine learning engineering and AI engineering at organisations ranging from startups to large corporates, and claims to have delivered tens of millions of pounds in value across various projects.

Obinna Iheanachor, AI/Data Engineer at Rotork and founder of Wisabi Analytics, follows with a case study titled From £8,000 to £40: What I Learned Shipping AI in a UK Engineering Company. The numbers are the story: a production system that extracts data from 4,700+ engineering drawings, brought down from £8,000 per run to under £40 by combining deterministic methods with LLMs rather than relying on a cloud-only approach. The talk covers when to call a model, how to manage cost versus accuracy trade-offs, and what breaks at scale.

The event is hosted by Parallax, a Leeds-based digital agency. It runs from 6pm to 8pm BST, with food served from 6pm on a first-come, first-served basis. The meetup is free to attend and organised by Jumping Rivers under the Leeds Data Science Meetup banner, which has been running regular sessions for the Leeds data community for several years. Anyone interested in speaking at a future event can contact the organisers at lds@jumpingrivers.com.

Why attend

Both talks are grounded in production experience rather than theory. Carney has shipped data and AI projects at scale across multiple industries; Iheanachor has a specific, quantified case study from a UK engineering company. If you work in data, ML or AI engineering and want to hear how practitioners are handling the cost and reliability problems that come with LLM-based systems, this is a practical evening.

The format also gives you 45 minutes of networking over food before the talks begin. Leeds Data Science Meetup draws engineers, data scientists and analysts from across the city, so it's a reasonable place to meet people working on similar problems.

Agenda

• 18:00–18:45 — Refreshments (food served first come, first served)
• 18:45–18:50 — Welcome
• 18:50–19:25 — John Carney (PDFTA): Building Valuable Deterministic Products in a Probabilistic World
• 19:25–20:00 — Obinna Iheanachor (Rotork): From £8,000 to £40: What I Learned Shipping AI in a UK Engineering Company

Speakers

• John Carney — Principal Consultant at PDFTA; co-founder of PyDataMCR; chair of PyData London Conference and the PyData Strategic Committee; co-founder of the Field of Play conference.
• Obinna Iheanachor — AI/Data Engineer at Rotork; founder of Wisabi Analytics, focused on production-ready AI for data professionals.