AI engineer · data, cloud & production systems
I turn recurring research, planning, and content work into applications people can use. My background in data engineering, cloud infrastructure, and production operations shapes how I build them: reliable data, visible failures, and clear points for human review.
See how the systems evolvedI own the architecture, implementation, and operating decisions documented in these case studies.
A repeated engineering pattern
Flagship systems
A training platform and a job-search workflow show how I carry an idea through data design, application development, and day-to-day operation.
Health & performance intelligence
CoachAI → Apex Human Hybrid
I built a training platform that brings workout history, recovery signals, route analysis, and race outcomes into one place. It grew from CoachAI when repeatedly loading years of history consumed too many tokens and credits. I designed the database, APIs, readiness calculations, and web and mobile clients so coaching can work from structured training data.
Career workflow & evidence governance
Repeated application work needed shared state outside the chat. I built Job Hunt OS across Google Sheets, Apps Script, scheduled Python and Playwright workers, multi-provider review, and document validation. It collects, verifies, scores, and packages opportunities; I review each packet and submit every application manually.
Applied engineering
Learning missions and earned arcade time
I built a privately hosted learning application shaped by my son's feedback, with 3,158 playable missions and four reusable game engines. An offline AI pipeline prepares content, while practice sessions, mastery tracking, and arcade rewards run in the browser.
Read the case studyPublic records into useful business research
I built a pipeline that turns Texas permit records into business research and assets ready for review. It preserves source history and human notes in Google Sheets, with 6,100+ normalized records and 98.7% coordinate coverage in the local artifact set.
Read the case studyOperating and modernizing WordPress Multisite
I operate and modernize a production WordPress Multisite platform with checksum-gated changes, custom OIDC identity, focused MU plugins, and offline AI content validation. Fourteen tests check claims, dates, and affiliate markup before editorial review.
Read the case studyProduction operations
I build the schedules, workers, and shared services behind these applications. Recovery and maintenance are part of the work.
Apps Script schedules, launchd jobs, and Python or Playwright workers execute recurring collection and rendering tasks. Recovery ledgers preserve workflow state after an interrupted run.
Job Hunt OS · macOS automationI run shared container infrastructure across several projects, including Home Automation. The upcoming case study will explain how the services are deployed, connected, and recovered.
Shared infrastructure · Home AutomationThe full-stack case study will cover the shared container platform, integrations, automation rules, state, recovery, privacy boundaries, and operating history.
View coming-soon noteEngineering foundations
Deterministic systems reliability
I built tools to keep older Macs useful and their data recoverable. Shell and Python automation handle storage, network mounts, verified file transfers, and PostgreSQL backup mirroring. Restore checks and tested retention rules govern when older backups can be removed.
Deterministic system Read the engineering studySystems contained inside hosted LLMs
The Travel Agent and Pokédex Reviewer use system instructions, structured knowledge, memory boundaries, ordered gates, and output contracts as their application layer. Their full operating boundary remains inside the hosted model environment.
Hosted LLM systems Explore the systemsEngineering point of view
My experience with data platforms, cloud infrastructure, and production operations shapes each AI design. I build deterministic systems for probabilistic models: software holds the facts and checks the output, models handle interpretation, and people retain consequential decisions.
More about how I workRoles and project work
I am interested in AI engineering, data platforms, and production systems. Send me the role or the workflow you want to improve, and we can discuss where my experience fits.