Domain context
Water operations, hydrology, treatment context, telemetry, lab data, and the constraints behind operational decisions.
About me
I work at the intersection of water infrastructure, software systems, data platforms, and applied AI.
Software foundations
Internal platforms, SDKs, APIs, validation gates, documentation, and delivery practices that can survive beyond a pilot.
Applied AI
Practical AI adoption in operational settings, from tooling and workflows to governance and team practice.
What I do
I’m most useful where the problem isn’t just writing code, but deciding what system should exist. I build data and software for infrastructure teams, with a focus on drinking-water operations, internal platforms, and practical decision support, sitting between product discovery and implementation, then turning useful prototypes into capabilities that can be reviewed, maintained, and adopted.
At Dunea, a drinking-water utility, I work on reusable Python tooling, digital-twin concepts, internal applications, simulation workflows, and practical AI adoption. Several of these are now in daily use across teams. Increasingly I also coach new engineers and help a growing data team turn prototypes into software it can support.
Current through-line
Turning operational knowledge into software that other people can inspect and maintain: telemetry, lab context, treatment assumptions, scenarios, validation, and paths toward solver-backed analysis.
The judgment that matters most is knowing what to build versus what to buy, and treating ownership, documentation, and governance as part of the product, not paperwork added afterward.
Background
My path started in civil engineering and water management at Delft University of Technology. Fieldwork in Thailand and Indonesia gave me a lasting respect for the physical, social, and institutional realities behind infrastructure problems.
That combination still shapes how I work. I care about models and code, but also about what happens before and after them: data quality, domain language, workflows, incentives, documentation, and the ability for other people to maintain what has been built.
How I frame the AI part
AI shortens implementation cycles, but the value depends on the person steering it understanding the domain, the architecture, and what still needs to be validated.
References
Research & public context
Some of my work has public reference points, even though most implementation details remain internal.