Senior Frontend Engineer / Frontend Architect | Full-Stack delivery — React · Next.js · TypeScript · Node · Applied AI

• About career: 13+ years of professional software engineering, primarily focused on the frontend. I've architected and implemented multiple web platforms from scratch, led engineering teams, and integrated frontier technology into projects whenever it drives real business value. Programming is both my career and my hobby.
• About side-projects: I do open-source tools for real-world problems (mostly things I rely on myself daily) and write technical articles on freeCodeCamp, Dev.to, and Medium.
• About self-improvements: I hold multiple professional web certifications alongside DeepLearning.ai specializations.
• About AI: I've been working with AI since it appeared on the market - ranging from custom ComfyUI workflows to my own local-first AI agents powered by llama.cpp etc., - and I help teams integrate AI into their daily workflows and products.

barbutsa.com — Source and live implementation of my Astro and TypeScript portfolio, with architecture checks, generated CSP, accessibility and performance work, 100 lighthouse, and full-sitemap browser tests. View the live website.

Zharwing Memory — Local-first, project-scoped memory for AI coding agents. A TypeScript monorepo with a React/Tauri interface, daemon, CLI, MCP integration, privacy boundaries, documentation, old docs imports with automatic ai relationship.

llamail — Your private agent, running locally. Control Gmail from Telegram: LLM-as-router intent classification, hybrid RAG search (ChromaDB + SQLite FTS5), drafting, campaigns, scheduled sends. Runs on consumer hardware - zero cloud, zero monthly bills (it has it's own personality and can talk with you like you favorite character :) ).

small-context-rag-solution — Python + TypeScript patterns for RAG under small context windows: summaries, raw chunks, and context-budget tracing. Companion code to my freeCodeCamp article.

• How to Handle Small Context Window Limits in RAG Systems — freeCodeCamp
• How I nearly doubled my premium model capacity without paying more — Medium
• The 3-Tier Memory System That Cut My AI Coding Context by 96% — Medium
• LLM as Router: Intent Classification for a Local Telegram Email Agent — dev.to
• How Search and Ask Work: Local Hybrid RAG with ChromaDB + SQLite FTS5 — dev.to
• From Inbox to Character: Building a Private Local AI Email Agent — dev.to

Frontend: React, Next.js, TypeScript, React Native, Astro, Redux/MobX, GraphQL, tRPC, Tailwind, design systems, accessibility, i18n Backend & platform: Node.js (Nest.js, Hono), Python (Django, FastAPI), Cloudflare Workers / D1 / R2 / KV / Durable Objects, WebSockets, Docker, CI/CD AI engineering: OpenAI & Gemini APIs, RAG (Vectorize, AutoRAG, ChromaDB, SQLite FTS5), embeddings, LLM routing, local LLMs (llama.cpp), LangChain

LinkedIn · StackOverflow (5k+ rep) · dev.to · Medium · sviatoslavbarbutsa@gmail.com