Senior Full-Stack Engineer & AI Architect

Digital brutalism architecture. Sites that are not templates, but manifestos.
Virtual employees who never sleep. Autonomous agents and workflows.
High-throughput e-commerce. Conversion enforced by design.
Search engine dominance. Technical SEO that devours the competition.
Optimization for AI engines. Be the answer ChatGPT and Gemini give.
Content that sells. Articles that rank #1 and convert readers into customers.
I don't just "build websites". I deploy scalable, automated digital ecosystems. Every commit triggers a chain reaction of optimization.
Next.js Compilation Static Generation
Unit Tests Accessibility Check
SEO Vector Injection Content Hallucination
Edge Network Global CDN
Analytics platform monitoring Brand Share of Voice in LLMs. 'LLM-as-a-Judge' architecture for automated visibility and sentiment scoring.
Intelligent financial hub with Smart SPA Fallback architecture. 90% editorial automation via Gemini AI and Python Serverless.
Autonomous agentic system generating 11,000+ SEO landing pages. Hybrid AI architecture (Gemini + GPT-4o) with real-time market discovery.

Internal BI Dashboard for a marketing agency. Aggregates SEO, Ads, and Work Logs into a real-time profitability engine.

Zero-drop WooCommerce → PrestaShop migration. Technical SEO, Core Web Vitals and Generative Engine Optimization for a beauty & fashion store.

Brand entity architecture, topical authority across 14 clusters, and GEO engineering for a Polish slow fashion brand. +180% branded searches, +65% organic revenue.

Bespoke ERP and AI system for a general contractor. Saldeo API integration, RAG engine on 70 cost estimates (3.2 GB), real-time Slack budget alerts.
/// TRANSMISSIONS
How to stop parsing strings from GPT and start getting data ready to use in code — JSON Schema, Pydantic and the Instructor library.
How to cut your OpenAI API bill by 60–80% without reducing response quality — prompt caching, model routing and conversation history compression.
Naive RAG with RecursiveCharacterTextSplitter fails on complex documents. How to implement semantic chunking, hybrid search with BM25, RRF fusion and Cross-Encoder reranking — with full production-ready code and RAGAS evaluation.
Initiate protocol. Establish connection. Let's build something loud.