Services / Engineering
Software, sites, and apps. Built at the size you need.
A one-page site, a web app, or a multi-region agent platform. Same engineer, same discipline, hosting and domain included.
I take on software at the size you actually need. A one-page site for a local nonprofit and a multi-region agent orchestrator at Zendesk get the same engineer and the same design discipline. I write code, I review code, and I sit in the design discussions that decide which problems are worth carrying forward. Hosting, domain registration, and the day-to-day operations of what I build can come under one predictable bill, so a busy month does not turn into a surprise invoice.
What I work on
Websites and web apps. Brochure sites, marketing pages, mobile-first builds, small-business tools, internal apps. Fast to load, easy to hand back, hosting and domain handled.
Agentic systems and orchestration. Multi-agent architectures framed as selection, expansion, simulation, and the backup phase most production systems omit, behind a stable interface the rest of your code does not have to learn.
LLM infrastructure. Inference routing, prompt and tool versioning, evals you can run on every PR, model swap without a rewrite, cost and latency budgets enforced rather than aspired to.
Production AI workflows. Job queues, retries, idempotency, tracing across model and tool calls. The unglamorous half of agent systems, where most outages live.
Large-scale distributed backends. Twenty plus years of Ruby, Java, JVM-adjacent stacks, and the kinds of platform problems that show up when a service goes from one region to many.
Technical leadership and incident response. Staff and Principal level work: design review, mentoring, hiring calibration, on-call rotations that are humane, postmortems that change behavior.
How I engage
Advisory. A few hours a week. Design reviews, architecture sessions, hiring and team-shape input. Useful when there is a strong team that needs a senior outside read and someone to call when the on-call goes sideways.
Embedded. Half time to full time, integrated into the team. I code, I review, I carry pages. Useful when there is a hard problem and the team wants a senior contributor rather than a slide deck.
Project-based. Scoped delivery against a written outcome with a written end. The team can be large or nonexistent: a multi-team platform build or a single site for an owner with no engineers on staff. I write the scope before the contract, ship it, and hand back something you can run, or keep hosting and operating it if you would rather not.
How I work
Plan first, then implement. I write the design before the code and circulate it for review. I bias toward small, reversible changes and explicit tradeoffs in writing. I do not ship work I cannot operate.
When something breaks, I run the incident rather than freelance through it: brief early, name the unknowns, keep changes deliberate under pressure. Production AI systems need that discipline as much as any backend does.
Representative outcomes
Work that has shipped, framed for a peer.
- Production agentic orchestration at Zendesk: multi-agent assembly of structured outputs from raw inputs, with a Critic revision loop, behind a stable interface that the rest of the product code did not have to learn.
- Distributed backend platforms at Best Buy and Wells Fargo: large-scale services with the unsexy operational properties (idempotency, retries, tracing, capacity planning) that keep them up.
- Hands-on technical leadership: design reviews, mentoring, hiring calibration, and on-call rotations that engineers stayed in.
- Sites, web apps, and internal tools delivered end to end for small teams and solo owners: shipped, hosted, and handed back running on a predictable bill.
Not the right fit
What I am honest about not taking on.
- Pure prompt engineering with no production target. If the work ends at a demo, I am not the right hire.
- Greenfield startup CTO with fundraising as the primary deliverable. I build, I do not pitch.
- Pure managerial roles with no code review or design contribution. I lead by writing, not by status meetings.
- Single-shot RAG over a static corpus presented as an AI strategy. Happy to advise on the underlying retrieval; not the product I want to build for you.