I integrate LLMs into products that ship. 14+ years building at scale—from Claude and OpenAI APIs to RAG systems processing thousands of queries daily.
From concept to production—integrating LLMs into real workflows
AI assistant for program managers automating task workflows. Built with Claude API, LangChain, and Vercel AI SDK.
Virtual AI assistant for security researchers. Improved bug submission quality by 25%.
Slack bot with RAG architecture for real-time company knowledge queries across teams.
Tools I use to ship AI products fast
const response = await anthropic.messages.create({
model: "claude-sonnet-4-20250514",
messages: [{ role: "user", content: prompt }],
});Shipping on nights and weekends
Building AI-powered products for the largest Web3 bug bounty platform. Architected Guardian AI, Hackoon, and internal RAG systems.
Led 18-engineer web team for high-traffic e-commerce (~$400M+ revenue). 25% performance improvement, 40% fewer deployment errors.
Led Next.js migration achieving 45% rendering speed improvement. Architected systems for 50% traffic growth with zero downtime.
Modernized legacy systems, built microservices, created component libraries. Published "Learning Ext JS 4" with Packt Publishing.
I'm open to AI engineering roles, consulting, or interesting projects.