Jake

What I work on

For the last few years I've been working on a payments platform that automates tax remittances at high volume, across many jurisdictions. The work is distributed systems plus financial correctness plus regulatory complexity, all at the same time. Every payment has to be auditable, recoverable, and reconcilable against a half dozen other systems it talks to. The cost of getting it wrong is real money going to the wrong place.

I tend to focus on the structural parts of systems like this. State machines that orchestrate how a payment moves through the pipeline. Document models where illegal states can't be represented. Module boundaries that don't fall apart as the codebase grows. And the operational tooling a small team needs to actually keep it all running.

Where I'm heading

The problems I've been solving in payments show up again when you think about AI agents in production: how do you bound what the thing is allowed to do, how do you design escalation paths when it's unsure, how do you enforce invariants at runtime, how do you recover when it goes wrong, how do you keep an audit trail that's actually useful.

I think of agent infrastructure as distributed systems work more than research work. Models are going to be wrong sometimes. What matters is whether the platform around the model can still enforce the properties you care about when that happens.

That's where I want to go next.