What I Do
Always Growing, Always Building
Staying sharp by building with emerging AI tools, mastering new frameworks, and integrating what works into production.
Learning as a Practice
AI moves fast. What was cutting-edge six months ago is table stakes today. After 13 years in enterprise engineering, I've learned that staying relevant isn't about chasing every new framework — it's about building a strong foundation and knowing when a new tool genuinely solves a problem worth solving. That instinct is what led me from enterprise infrastructure into AI engineering full-time.
I make learning a daily habit. Whether it's reading source code, building a small prototype to test an idea, or writing about a concept to solidify my understanding, I treat every project as an opportunity to level up.
Sharing knowledge is part of the process. Writing technical articles, documenting decisions, and explaining complex topics in plain language helps me think more clearly and gives back to the community that I've learned so much from.
How I Learn
Build to understand
Prototypes and side projects over tutorials alone
Read the source
Documentation is good; understanding how things actually work is better
Write to think
Technical writing forces clarity and reveals gaps in understanding
Teach what you know
Explaining a concept is the best test of whether you truly grasp it
Current Focus Areas
Agentic AI Systems
Multi-agent orchestration, MCP server architecture, and building intelligent assistants that solve enterprise problems.
RAG & Semantic Search
Vector databases, embeddings, and retrieval pipelines for enterprise knowledge bases.
AI Developer Tooling
Claude Code, Cursor, GitHub Copilot — and building internal automation tools to accelerate AI workflows.
Technical Communication
Translating complex AI and systems concepts for both engineering teams and senior leadership.
See what I've been writing about
Browse Articles →