Resume / Bio

Full-stack product engineer for early applied AI work.

I write software, but I do not start with code. I start with the system: the workflow, the people, the data, and the decision the product needs to support.

The resume below is the formal version. The short story is simpler: I came to AI through real problems in solar, property, markets, and personal agent workflows, then kept building tools around the parts that felt unclear or underspecified.

Open PDF resumeDownload DOCXRead resume

Formal resume

Alex Horton

Full-stack product engineer · Applied AI · 0→1 product work
Santa Cruz, CA
horton.alexander@gmail.com
alexhorton.dev

Profile

Full-stack product engineer focused on applied AI, workflow tools, data products, and early product systems. I am strongest where the product shape is still forming: mapping the workflow, building the first useful version, connecting APIs/data/UI/LLM tooling, and iterating with users or product-minded teams.

Skills

Full-stack: Next.js, React, TypeScript, Tailwind, Node, FastAPI-style APIs, Python, REST APIs, PostgreSQL/Supabase, DuckDB, auth, schema design, scheduled data pipelines, Vercel, Docker, GitHub Actions.

AI/data: LLM workflows, Claude Code/Cursor/Hermes, tool-calling loops, OpenRouter/model routing, RAG patterns, persistent context, Pandas, NumPy, scikit-learn, XGBoost, feature engineering, backtests, evaluation loops.

Product: MVP scoping, user interviews, workflow mapping, dashboards, data visualization, ROI modeling, product analytics, technical translation.

Experience

Builder, full-stack product engineer · IndependentSanta Cruz, CA · 2019–present
  • PropFi: Built a property analytics product that moves portfolio review out of scattered CSVs, PDFs, and ad-hoc emails into a single tool for financial views and shareable client reports.
  • Energy Scout: Built a consumer solar calculator that combines production assumptions, incentives, quote data, and ROI into a personalized report for homeowners evaluating solar.
  • Bitcoin ML: Built a public quant research site around Bitcoin price drivers, Python data pipelines, feature tests, walk-forward backtests, and reproducible dashboards.
  • Agentic workflows: Built and used a coordinated AI development/workflow system with Claude Code, Hermes-style agents, model routing, persistent context, scheduled jobs, Telegram, and voice summaries.
Solar market analyst / consultant · Day One Solar + independent2016–2019
  • Analyzed utility rates, incentives, consumption data, permitting constraints, and site economics for commercial, agricultural, multifamily, and community-solar opportunities.
  • Built ROI models, market analyses, mockups, and stakeholder-ready feasibility materials that translated technical solar details into clearer business recommendations.

Selected work

Hermes / personal agent system: applied AI workflows with scoped agents, memory, tools, project context, Telegram, scheduled automations, and voice summaries.

Energy Scout: solar ROI and incentive decision support.

Bitcoin ML: supervised ML and quant research across macro, price, and on-chain data.

PropFi: property analysis, SQL/data workflows, uploads, APIs, and investment/reporting surfaces.

Aquaponics / vermiponics: hands-on sustainability systems that shaped my physical-systems/product instincts.

Education + credentials

Cal Poly San Luis Obispo, B.S. Liberal Arts & Engineering Studies, Technology / Sustainability / Product Design, Cum Laude, Engineering Academic Excellence Award. MIT Professional Education Applied Data Science. Stanford Online Supervised Machine Learning. Anthropic Claude / Claude Code coursework. Google UX Foundations.