I'm a Senior Full-Stack Engineer specializing in building AI-powered products that transform how businesses operate. Currently at Forum3, I help consumer companies adopt AI First approaches—integrating artificial intelligence as a core element of their products, services, and decision-making processes.

I architect end-to-end solutions that make AI practical and measurable. Recently, I engineered an automated insights platform that analyzes customer reviews at scale using LLMs, complete with a quality control system that effectively prevents attribution errors. I've built everything from multi-step onboarding experiences with savings projections to LLM-powered chat systems with file processing—always focusing on delivering real business value. My approach combines deep technical skills in TypeScript, React, Next.js, and Python with hands-on experience integrating multiple LLM providers (OpenAI, Anthropic Claude, Google Gemini) and implementing AI patterns like RAG and ReAct agents.

What drives me is the challenge of making AI work reliably in production. I believe in building robust systems with proper validation, testing frameworks that catch edge cases traditional unit tests miss, and quality controls that prevent errors before they reach users. Whether I'm architecting a playbook system for executive analysis or building distributed applications for Web3, I focus on creating solutions that are both technically sound and genuinely useful.

Through my freelance work at Wild Hare Technologies, I've led projects ranging from financial assistance chatbots to Web3 decentralized applications. I've learned that the best AI products come from rapid iteration, gathering real user data early, and establishing feedback loops that drive continuous improvement.

I'm passionate about the intersection of AI and practical software engineering, and I'm always exploring new tools and patterns—from Model Context Protocol (MCP) and Claude Code to context engineering and AI-assisted development workflows. I stay current with evolving best practices like regularly updating coding rules, refining tool integrations, and optimizing error feedback loops to maximize AI effectiveness. If you're working on AI-powered products or interested in discussing how to make AI work in production, let's connect.