AI Engineer · Educator · M.S. Applied AI, Neumont University
Ten-plus years of software engineering, now sharpened by a Master's in Applied AI — RAG architecture, multi-model LLM orchestration, and ML data pipelines built end to end, from raw data to production. Currently building Lorekeeper.quest as a graduate capstone.
About
I'm an AI-focused engineer based in Ogden, Utah, working daily at the intersection of model behavior and deployable software. My background is classic software engineering — backend services, SQL systems, CI/CD pipelines — and for the past several years I've been deliberately rebuilding that foundation around AI: RAG pipelines, multi-model orchestration across Claude, Gemini, and ChatGPT, local LLM hosting, and the ML data work that makes any of it trustworthy.
My M.S. in Applied Artificial Intelligence at Neumont University (expected September 2026) has been the forcing function to go deep on the parts of the stack a bootcamp skips: full ETL pipeline design, data sanitization, model training and evaluation in TensorFlow and PyTorch, and the statistics behind knowing whether a model is actually working. I pair that coursework with real production responsibility — building the evaluation framework for a live AI agent at Blytz, and shipping data pipelines that executives actually read.
I build with AI-assisted tooling as a first-class part of my workflow — Claude Code in particular — not to skip the engineering, but to move faster through it while staying accountable for every architectural decision underneath.
Neumont University, Salt Lake City, UT — expected September 2026
Model training & evaluation (TensorFlow, PyTorch, ML.NET) · RAG architecture · full ETL & data-sanitization coursework
Weber State University, Ogden, UT
Graduate-level data science coursework completed as an undergraduate: data cleaning, predictive modeling, mathematical frameworks
Graduate Capstone
Lorekeeper.quest is my M.S. capstone project — a live, evolving system that takes a body of raw data all the way to an AI-powered, user-facing product. It's the single project where every stage below had to work together, not just in isolation.
Designed pipelines to pull raw source data in reliably and repeatably, treating ingestion as production infrastructure rather than a one-off script.
Sanitized and normalized messy, inconsistent source data — the unglamorous work that determines whether anything downstream can be trusted.
Engineered features and structured schemas purpose-built for both model training and fast, RAG-ready retrieval.
Trained and evaluated models against real accuracy metrics — iterating on what "good enough" means for a production feature, not a notebook demo.
Turned pipeline and model output into interfaces people can actually read and act on — the same discipline behind executive dashboards, applied to a consumer product.
Implemented retrieval-augmented generation and multi-step orchestration logic so the system reasons over prepared data instead of hallucinating around it.
Every stage above is easy in isolation and hard in combination. The real lesson of Lorekeeper.quest has been that RAG quality is a data quality problem — orchestration logic can't compensate for a bad chunking strategy, and a beautifully trained model is worthless if the visualization layer buries the answer a user actually needs. Building it end-to-end, with Claude Code as an AI pair-programmer throughout, also reshaped how I write software: I spend less time on boilerplate and more time on architecture decisions, prompt and retrieval design, and evaluating whether the system's output is actually correct — the skills that matter most once AI is writing alongside you.
Selected Work
A full-stack JavaScript application integrating RAG architecture, local LLMs (Ollama, KoboldCpp), and hosted model APIs to orchestrate complex, multi-step tool-use logic. Architecture designed, built, and evaluated end-to-end.
Full-lifecycle model development — data sanitization, ETL, training, evaluation — in Jupyter and ML.NET, deployed as a working image-classification application.
GitHub Actions pipelines that compile and deploy production builds directly to a live website, owning the full deployment path from commit to production.
Experience
Blytz
Common Thread
Salt Lake Community College
Hill Air Force Base · Instructure (Canvas) · Microsoft · Control4
Full role history on linkedin.com/in/hsmith-dev
Technical Skills
RAG architecture design · prompt engineering · multi-model API integration (Claude, Gemini, OpenAI) · local LLM hosting (Ollama, KoboldCpp) · agentic tool-use orchestration
TensorFlow · PyTorch · ML.NET · model training & evaluation metrics · classification models · human-in-the-loop evaluation frameworks
ETL pipeline design · data sanitization · feature preparation · SQL / BigQuery · Python (pandas, Jupyter)
Python · JavaScript · C# · REST API design · Git · GitHub Actions CI/CD · Google Cloud Platform · Amazon Web Services · Linux
Availability
I've spent years as an AI Trainer at Salt Lake Community College and bring that same teaching instinct to workshops, mentorship, and technical training — making RAG, LLM orchestration, and applied ML approachable for engineers and teams who are new to them.
I design and build AI capabilities into existing software — RAG search, LLM orchestration, evaluation pipelines, and data infrastructure that makes AI features trustworthy in production, not just in a demo.
Get in Touch
Based in Ogden, Utah — open to AI development work and teaching engagements, remote or local.