About Me

My core expertise lies in building AI systems with production-grade reliability. I work with LangChain, LangGraph, and RAG architectures to create intelligent applications — from conversational agents with memory and tool use, to multi-agent systems where specialized AI workers collaborate to solve complex problems. I design structured output validation, automatic fallbacks between LLM providers, and observability pipelines with Langfuse so every token and cost is tracked.

On the backend side, I architect scalable systems using NestJS, Express.js, and PostgreSQL. One of my recent achievements is applying CQRS with a ClickHouse OLAP read projection and materialized views behind a 4-level query cascade, cutting p95 dashboard queries from ~5s to under 200ms on a dataset of 300M+ rows. I build event-driven architectures, background job processors with BullMQ, and APIs that handle real-world scale without breaking.

For frontends, I work with Next.js, React, and TypeScript to build fast, SEO-optimized applications. I care about performance, accessibility, and clean component architecture. Whether it's server-rendered pages for crawlability or real-time dashboards with WebSocket updates, I choose the right rendering strategy for the job.