Available for AI Full Stack roles · Scottsdale, AZ

16+ years of engineering.
Now building with AI.

Senior Frontend / Full-Stack Engineer specializing in React and modern web architecture, currently building production-grade Agentic AI systems — RAG pipelines, MCP servers, and streaming agents.

Explore my work → GitHub ↗
PHP
→
JavaScript
→
React
→
Full Stack
→
Cloud
→
Agentic AI
02 — Selected Work

Things I've built

AI Agent · P1
↗

Calendar Scheduling Agent

Agentic loop that schedules meetings from natural language. Provider-agnostic — Ollama locally, Anthropic in production.

Agentic Loop Tool Use Node.js
New concept while(stop_reason === "tool_use")
RAG + Agent · P2
↗

IT Support Agent

Diagnoses and fixes VPN and tool access issues using RAG + parallel tool calls. Searches docs before acting.

RAG Parallel Tools Node.js
New concept JSON keyword RAG + parallel tool calls
● Live · P3
↗

Site Search Agent

Semantic product search solving vocabulary mismatch — "footwear for jogging" finds running shoes. Voyage AI embeddings + Neon pgvector + Anthropic Claude.

Voyage AI pgvector Cosine Similarity Neon Postgres
New concept Real embeddings + two-phase RAG pipeline
● Live · P4
↗

Restaurant Agent + MCP

Food recommendation agent with all production patterns. MCP server exposes 5 tools — any AI connects via SSE URL. Streaming SSE, Redis cache, Bottleneck rate limiting.

MCP Server Streaming SSE Redis Cache Bottleneck Zod
New concept MCP protocol + streaming + production patterns
Built · P5
↗

HR Onboarding Agent

Fully onboards new employees — creates accounts, assigns equipment, then pauses for manager approval via webhook before sending welcome email. Resumes from exact state.

Human-in-the-loop Webhook Resume Persistent State Idempotency
New concept Pause → save state → webhook → resume
● Live
↗

Autism Worksheet Studio

Free AI tool generating PECS cards, visual schedules, and social stories for autism families. Built as a parent who needed it. ARASAAC pictograms. AGPL-3.0.

React 19 Hono Cloudflare Workers Anthropic Claude
Purpose Built for families who needed it — free, open source
03 — Engineering Experience

16+ years of building

2009
Programmer Analyst
PHP · Perl · Oracle Endeca · jQuery · Drupal
↓
2014
Senior Frontend Engineer
React · TypeScript · Redux · Adyen Payments
↓
2020
Lead Frontend Engineer
React Architecture · TanStack Query · Node.js · AWS
↓
2026
AI Full Stack Engineer
Agentic AI · RAG · MCP · Cloudflare Workers · Neon
Frontend
React 19 · TypeScript · Redux Toolkit · TanStack Query · Vite · HTML · CSS
Backend
Node.js · Hono · Express · REST APIs · Drizzle ORM · Neon Postgres · pgvector
Cloud & Infra
Cloudflare Workers · AWS · Upstash Redis · Voyage AI · GitHub Actions
AI Engineering
Anthropic Claude · Agentic AI · RAG · Embeddings · MCP · Streaming SSE · Zod
04 — AI Journey

6 months building AI agents

Every concept learned by building — not just reading. From the first agentic loop to production patterns with MCP.

Month 01
Agentic Foundations
✅ Agentic loop pattern
✅ Tool use — LLM decides, code executes
✅ Provider-agnostic architecture
✅ Calendar Scheduling Agent
Month 02
RAG + Knowledge
✅ RAG — JSON keyword search
✅ Parallel tool calls
✅ System prompt design
✅ IT Support Agent
Month 03
Embeddings + Vectors
✅ Voyage AI embeddings
✅ pgvector cosine similarity
✅ Vocabulary mismatch solved
✅ Site Search Agent
Month 04
MCP + Production
✅ MCP server — 5 tools via SSE
✅ Streaming SSE to React
✅ Redis cache + Bottleneck
✅ Restaurant Agent
Month 05
Human-in-the-Loop
✅ Pause + resume via webhook
✅ Persistent state to Neon DB
✅ Idempotent tool execution
✅ HR Onboarding Agent
Month 06
Multi-Agent Systems
🔄 Orchestrator pattern
🔄 Code Review Agent
🔄 Multi-MCP architecture
🔄 Evaluation + observability
05 — Core Concepts

The 5 layers of every AI agent

🧠
Model
Reasons + decides
encapsulated by
🤖
Agent
Loop + behavior
connects via
🔌
MCP
Standard bridge
calls
🔧
Tools
Execute actions
retrieves from
📚
Knowledge
RAG + memory
Project
Model
Tools
Knowledge
MCP
Special
P1 Calendar
✅
✅
—
—
Agentic loop
P2 IT Support
✅
✅
JSON RAG
—
Parallel tools
P3 Site Search
✅
✅
pgvector
—
Embeddings
P4 Restaurant
✅
✅
JSON RAG
✅
Streaming + Cache
P5 HR Agent
✅
✅
Neon DB
—
Human-in-loop
06 — Engineering Notes

Writing about what I build

All posts →
agentic-airag
The Agentic AI Stack — Every Layer, Mapped
Embeddings, vector stores, orchestration, memory, guardrails, observability. A full map of the agentic AI landscape and where each piece fits.
Aug 14, 2026
→
agentic-ailearning
6 Months of Building AI Agents — What I Learned
16 years of frontend engineering meets agentic AI. What actually matters, what surprised me, and where I'm going next.
Aug 3, 2026
→
tool-useagentic-ai
Tool Use — The LLM Decides, Your Code Executes
A deep dive into how tool calling actually works — the request shape, response shape, and the critical insight most tutorials miss.
Jul 21, 2026
→
productionagentic-ai
Production AI Agents — Queues, Rate Limits, and Cost Control
What separates a demo from production. The patterns that make AI agents reliable, affordable, and scalable.
Jul 14, 2026
→

Let's build something meaningful.

Open to AI Full Stack roles — direct hire or contract. 16 years of engineering + production AI experience.

Get in touch → View GitHub ↗