Software Engineer with expertise in AI/ML systems, full-stack development, and cloud solutions, specializing in LLM API integration for enterprise applications. Currently a Founding Engineer at Y Combinator startup building AI systems serving 10+ hospitals. Former Founder and CTO with experience taking platforms from concept to market. Proven ability to both develop technical products and lead business operations including marketing, sales, and operations.
Notes on building AI products — LLM systems, real-time architecture, and the things that actually break in production.
View All Posts →I joined as a senior engineer. In my first month I rewrote the data layer and built a versioned deploy system. Neither was on my JD. Here's why I did them anyway.
When a microservice goes down at 3am, the slow part isn't fixing it — it's figuring out which service is actually broken. We built an LLM agent that does the triage.
When users pay per minute for a call, the wallet is on the critical path. Here's how we used Redis-level reservations and locks to prevent double-billing and negative balances.
An LLM that does astrology readings sounds like a gimmick. Building one that feels like a different astrologer for every user is a real engineering problem.