About

I'm an AI architect. The qualifier I lead with is applied — my work is the platforms and pipelines and agents you can point at, not the strategy decks you can debate.

I spent the first half of my career shipping enterprise software inside insurance and banking. I now spend most of it shipping production AI on infrastructure I run myself. The two halves look different on a CV. In practice, they're the same job.

Now

Three production AI platforms, one infrastructure.

AngelsWorks Hub is the orchestration layer. 22 modules, 67 containers, a multi-tier LLM gateway routing ~90k free calls per day across 12+ providers with self-healing fallback, an RBAC model with trust scoring, and a Mission Control surface that turns the whole thing into something I can observe rather than guess at.

ArtLens is a vision pipeline for art identification. Iconographic deduction over expert-curated subject variants, forced-choice VLM prompting, an image-prep stage that surfaces details no model sees in raw thumbnails, and a self-training loop that promotes confirmed observations into diagnostic elements after three independent corroborations.

Tenant Manager is an MCP-native SaaS for landlord operations. 48 MCP tools, full Belgian rental law as a first-class domain, and agents that can run the business as long as the human confirms.

Before

Twenty years of enterprise SharePoint and .NET run underneath all of this.

Most of it was inside regulated environments — life insurance at AG Insurance, retail banking at KBC, energy at Electrabel — as a SharePoint and .NET consultant. At Electrabel I led the SharePoint development team through the SP2007 → SP2010 migration with production-deploy ownership. Between 2016 and 2018 I built the Contract Registration Tool at AG Insurance IS Life (via Aprico Consultants) on top of a legacy stack, and tracked down a two-year-old production bug that the team had learned to work around. Two and a half years at KBC in regulated financial flows followed. Behind all of that: a long consulting career through my own company (Engelen INC, 2008—present), and BaaN ERP work in the late '90s / early 2000s — plus CRM and BI engagements across manufacturing, finance, and beyond.

The point isn't the line items. It's that I learned how to ship and operate software inside organizations where just rewrite it wasn't a valid answer. That habit transfers.

What I'm looking for

Permanent AI Architect role, EU remote.

Ideally with a team that owns its AI platform rather than buying SaaS abstractions, where decisions about routing, evaluation, prompts, agent boundaries, and data are visible and revisable rather than hidden behind a vendor's roadmap.

Explicit non-goals, in the spirit of saving everyone time:

Not a freelance or consulting funnel. I've done that career, and stopped on purpose.
Not interested in pure-research positions. I like results that ship.
Not interested in pre-product-fit startups. I've built enough things from scratch on my own time; the next step is to do it inside a team where the surface area is bigger than what one person can hold.
Not chasing the highest comp number on the page. Looking for a team I'd want to spend years with.

How I work

Small, often, instrumented.

I write small, I commit often, I read the code before changing it. I prefer making one decision well and writing it down to making three decisions vaguely and revising later. I'd rather route every LLM call through a single gateway and pay the integration tax than scatter provider keys across services. I instrument before I add features. I'm comfortable in the boring parts — migrations, backups, observability, RBAC — because the interesting parts depend on them.

If you'd like more, the case studies have architecture sketches and the decisions behind them.