I'm Harrison Smith, a contract AI and data engineer. I scope, build, and ship production systems for businesses, not demos.
I spent a decade writing production software. Now I build the AI and data systems that keep businesses running on it.
I'm Harrison Smith, an independent AI and data engineer based in Ogden, Utah, operating under HSmithDev LLC. My background is classic software engineering: backend services, SQL systems, CI/CD pipelines. The last several years, I've rebuilt that foundation around AI, with RAG pipelines, multi-model orchestration across Claude, Gemini, and ChatGPT, local LLM hosting, and the data engineering that makes any of it trustworthy.
Day to day, I'm the Business Intelligence Analyst at BlytzPay, a Series A payments company, where I build the BigQuery models and dashboards Finance and Risk run on, and own the evaluation framework for their production AI agent. I bring that same production discipline to client work.
My M.S. in Applied AI pushed me deep into the parts a bootcamp skips: model training and evaluation, ETL design, and the statistics behind knowing whether a model actually works. I build with Claude Code as a first-class part of my workflow, to move faster through engineering, not skip it.
Neumont University. Model training and evaluation, RAG architecture, ETL and data sanitization.
Weber State University. Graduate-level data science coursework as an undergraduate.
Three ways I plug into a team that needs an engineer, not another meeting.
How an engagement runsI design and ship retrieval pipelines, multi-model orchestration, and agentic tool-use systems, then build the evaluation harness that proves they work before your users find out otherwise.
Currently own the evaluation framework behind BlytzPay's production AI agent.
I build the ETL pipelines and BigQuery data models underneath the dashboards your finance, risk, and product teams actually trust, then document every join so the next engineer trusts it too.
Validated roughly 150 table relationships in a production BigQuery data lake, now restructuring it into a medallion architecture.
Backend services, REST APIs, and GitHub Actions pipelines, scoped and shipped end to end. I own reliability for clients who don't have a platform team behind them.
Ongoing backend and SQL systems work for Common Thread's clients since 2024.
RAG quality is a data quality problem.
We start from your actual requirements, not a generic discovery deck. I scope the system, flag the risks, and give you a fixed plan before any code gets written.
I build in the open: working increments, real commits, and Claude Code as a first-class part of the workflow, not a replacement for engineering judgment.
Production means production: CI/CD, monitoring, and documentation, not a demo that only works on my laptop.
I stay reachable after launch. Most engagements include a support window, so the handoff is never a cliff.
Proof for the services above.
Open-source, multi-agent coding UI
A free, fully open-source (MIT) local app, in the spirit of herdr, for running Claude Code, Antigravity, Codex, Grok, or a local model from one browser UI instead of a terminal per agent. Permission cards before every command or edit, BMad planning and a live ticket board, and a UI you can theme down to the color.
Coming soon to iOS
Private voice notes with on-device AI
Records, transcribes with Whisper, summarizes, and pulls out tasks on iPhone and iPad. Every step runs on the device's own chip, even in airplane mode.
Sanitization, ETL, training, and evaluation in Jupyter and ML.NET, deployed as a working image classifier.
GitHub Actions pipelines that compile and deploy production builds straight to a live site.
BlytzPay
Build the BigQuery models and dashboards Finance, Risk, and Product run on, and own the evaluation framework for BlytzPay's production AI agent.
HSmithDev LLC
Scope, build, and ship software for businesses of all sizes, owning the full lifecycle from requirements to production. Consulting and AI workflow training for organizations including the PROG Development Center and Acord.AI, and subject-matter expert for Western Governors University's B.S. in Data Analytics with AI.
Common Thread
Backend services and SQL systems for a variety of clients, owning reliability with no platform team behind me.
Salt Lake Community College
SQL and JavaScript dashboards for stakeholder reporting, plus lead instructor for "AI @ Work," a workforce training series on prompt engineering and practical AI adoption.
Instructure, Control4, Education at Work
SaaS support for the Canvas LMS, IT systems administration, and Microsoft Office support.
Open to new engagements
HSmithDev LLC. Based in Ogden, Utah. Remote or local.