AI & Data Architecture — Las Vegas, Nevada
I build the AI systems companies
can't afford to get wrong.
Retrieval, agentic automation and document intelligence — architected on data platforms built to carry them, and delivered end to end. Discovery, pilot, production, and the runbooks your team operates it with.
Capabilities
Most AI work fails at the seams — between the model, the data underneath it, and the operational reality it has to survive. I work across all three, which is why the systems stay up after the engagement ends.
Retrieval-augmented generation, agentic automation and workflow copilots, designed around a client's actual data, tools and constraints — not a reference diagram. Document intelligence at scale where it genuinely moves the needle.
The layer everything else stands on. Modeling, warehousing and large-scale ETL that hold up under production load, audit and change — across cloud platforms and legacy systems that still have to be carried forward.
Systems that outlive the engagement. Infrastructure as code, CI/CD for models and prompts, observability wired to SLAs, cost governance, and the runbooks a client's own team needs to operate what they've been handed.
Selected work
Recent engagements, described at the level of the architecture. Client names are withheld where the work is under contract.
Scanned policyholder forms, taken end to end through a tiered pipeline that spends the cheapest possible resource first: deterministic catalog matching, then OCR, and only then a language model. Designed as a reusable pattern the client could redeploy across adjacent document workflows — not a single-purpose build.
Delivered solo as roughly 16,000 lines of production Python and Terraform, alongside thirteen operational and architectural documents — system overview, deploy runbook, subsystem references, pipeline blueprint, secrets wiring, DLQ triage — so the client's own DevOps team could take it from there.
Lead developer on moving unstructured documents off a legacy IBM FileNet estate into AWS, and on rebuilding an existing Camunda-based vetting workflow natively on the AWS side — both as custom multi-step architectures rather than a lift-and-shift that would have carried the old constraints across.
Also maintained and extended a Python ETL framework, and built a generic SQL-interfaced ETL tool that let two data teams run their own pipelines without the backend knowledge the previous process demanded. Recognized with the organization's Star Performer award.
Founded and architected a fitness logging and analytics product, directing consultant engineering and QA teams across mobile UI, data transfer services, backend infrastructure and the reporting engine.
Built a Python framework for preprocessing and model experimentation — including synthetic data generation, so a brand-new user gets a projected training path on day one instead of an empty dashboard — with models deployed as REST APIs on Azure ML for real-time inference.
Writing
Ten-plus technical titles across applied machine learning, perception, retrieval and real-time systems — each written to be the explanation I wanted when I first picked the subject up. Available on Amazon.
Frameworks
Perception
Retrieval
Real-time systems
Also the author of a 140-plus question guide for data architecture interviews.
About
I read Political Science at Cornell, then spent the next decade going the other direction entirely — from analytics and software engineering into data architecture, and from there into the applied AI work I do now. The detour turned out to be useful: most of what decides whether these projects succeed is not the model.
In 2023 I founded IntelliSoft Ventures to do this work directly with clients — custom AI implementations taken from discovery and acceptance testing through pilot and into production, tied to outcomes that can actually be measured. Before that I architected data and AI systems in federal healthcare, cloud consulting and product engineering.
I write, too. Ten-plus titles on the libraries and systems I build with, because teaching something is the fastest way to find out how well you understand it.
Based in Las Vegas, Nevada. Working with clients anywhere.
Contact
Whether it's an AI implementation you want taken seriously from the first week, or a data platform that has to hold up under what you're about to put on it — tell me what you're building.
contracts@intellisoftventures.com
