a profile in systems & craft
Ten years of frontend and design instinct, now spent building the AI infrastructure organizations can actually govern.
Before he wrote a line of code, Daniel studied how institutions work.
before i wrote a line of code, i studied how institutions work — universities, companies, the informal rules that hold an organization together when nobody’s watching. that turned out to be the right training for what i do now.
"The hardest part of any real AI adoption was never the model. It’s the governance around it."
these days the hardest part of any real ai adoption was never the model. it’s the governance around it — who’s allowed to use it, what data it can see, what happens when it’s wrong. that’s a sociology problem wearing an engineering costume, and it’s the one i’m best at.
He started building interfaces before "frontend framework" was even a settled term.
i started building interfaces before "frontend framework" was even a settled term — jquery, hand-rolled state, css that fought you every step of the way. then came the framework decade: angular end to end, enough react and vue to be dangerous, ngrx and redux for state that needed real discipline, component libraries and design systems instead of one-off pages, and tests, performance and accessibility that had to hold up in production — not just look right in a demo. i designed as much as i coded too — years of hands-on figma and adobe xd work built the instinct for what belongs in front of a user, even though these days that means reading a spec fluently, not drawing one, because a technically correct interface nobody wants to use isn’t actually done.
That decade taught him the thing a lot of AI-first engineers skip: taste.
that decade taught me the thing a lot of ai-first engineers skip: taste. knowing when a pattern is right for the people using it, not just correct on paper. now the tools have changed again — i build with ai assistance the way i once learned to build with frameworks, and the shift feels familiar rather than threatening, because i’ve already lived through one generational rewrite of how this work gets done.
that’s also where the mentoring comes from. i’ve watched this field reinvent its own tooling every few years, and the people who stay useful are the ones who can translate — between old code and new, between what a model suggests and what actually belongs in production, between an engineering team and the humans who have to live with what it builds.
Ten years of it, before anything else — the foundation everything below is built on.
A decade shipping production interfaces — Angular, React, Vue, state management that had to hold up, micro-frontend systems that scaled past one team, testing, performance and accessibility built in from the start — with the design sense to know what actually belongs in front of a user.
what he's building on top of it
What you build AI on top of, if it’s going to hold up — system boundaries documented arc42-style, not diagrams that go stale after the workshop.
Designing and shipping LLM-powered products — retrieval-grounded assistants and agentic workflows that get more accurate the more they’re used.
Provisioning and running the infrastructure AI products depend on — reproducible, auditable, built to survive an audit, not just a demo.
Building the policy layer that lets a company set its own rules for AI instead of inheriting a provider’s.
Responsible for front-end architecture and, increasingly, for the AI systems and infrastructure-as-code behind our products — including applied work on real-time governance and policy enforcement for LLMs. I mentor junior developers and work directly with clients, turning ambiguous requirements into production systems.
Front-end (mostly Angular) and back-end (Node.js, MongoDB) on a small, senior team — the training ground for owning a problem end-to-end instead of a single layer of the stack, across every stage of the product cycle.
Financed through a one-year scholarship by Forschungszentrum Jülich, we built an application connecting local companies with breakfast providers.
We adapted the PillPack model from the US for the German market. The proof-of-concept performed well; we ran into legal obstacles that ended the project.
Westfälische Wilhelms-Universität Münster. Analysis of the social structure of modern institutions and organizations. Worked as a research assistant to Dr. phil. Gallina Tasheva.
Katholische Universität Eichstätt-Ingolstadt. Politics and society, focused on organizational and industrial sociology. Worked as a research assistant to Prof. Dr. Joost van Loon.
you get someone who shipped production frontends for a decade, designed before he built, and spent the last few years turning ai from a novelty into infrastructure a real organization can trust — not three different people you’d have to hire separately.
He translates instead of picking one discipline and ignoring the rest.
i translate instead of picking one discipline and ignoring the rest: design and engineering, the old stack and the new one, technical depth and the people who actually have to live with what gets built. that’s the whole pitch.