Andrew Bottoni

I build systems that have to be right, not just impressive — where a confident wrong answer costs real money, and the engineering that catches it matters more than the model that produced it.

My current work is an orchestrated hierarchical multi-agent system for systematic investing: a coordinator that delegates research to tiers of local and cloud models, paired with a deterministic statistical gauntlet that decides what survives. The interesting engineering isn't the agents — it's the machinery that makes a swarm of fallible models produce trustworthy results.

But this is a recent chapter in a long book. I've been a working programmer since 1979 — portfolio and investment systems, payments, cross-platform desktop, mobile, and safety tech — and a critical-care paramedic the entire time. The engineering heritage has the full forty-year arc and the story of how the two careers feed each other.

What I'm good at

• Multi-agent orchestration — supervisor/worker hierarchies, cost-tiered routing across local GPUs and cloud APIs, reproducible isolated execution.
• Quantitative evaluation — permutation tests, deflated Sharpe, bootstrap robustness, walk-forward and regime analysis; turning "trust me" into "re-run this and see."
• Full-stack systems — data pipelines, dashboards, automation, alerting, and the operational discipline to run them unattended.

Two reasons you might be here

You have a hard problem. If you're a company facing something that doesn't fit an off-the-shelf tool, that's exactly the work I want. I operate through MICP.

You're stuck on something I've solved. I write up the non-obvious problems and their fixes in my notes, and document the larger system in the HMAS white paper. If it saves you a week, that's the point.