Production automation for content operations at scale — n8n, FastAPI, RAG pipelines, self-hosted LLMs. I architect the infrastructure that lets small teams ship the output of large ones.
Currently leading SEO & Automation Engineering across a network of 330+ sites in 52 GEOs, with a 15-person team and an in-house AI stack running on Hetzner, Cloudflare and a self-hosted RTX 4090. Internal builds include a multi-region monitoring SaaS, a network-wide analytics platform, and an AI content pipeline shipping ~100 titles/day.
[ NOTE ] All projects below operate under client confidentiality. Names, domains and screenshots are intentionally omitted — happy to walk through architecture and outcomes under NDA.
Senior-level AI automation engineering — engagement formats range from full-time contract to fractional tech lead to project-based audits.
End-to-end design and implementation of production AI systems for content and data operations: n8n orchestration, FastAPI microservices, RAG pipelines, MCP servers, agentic workflows.
Production-grade workflow design and review. From simple integrations to 190+ node pipelines with error handling, queues, batching and observability. Performance audits with concrete fixes.
Vector search architecture (Pinecone, embeddings), retrieval pipelines, self-hosted LLM inference on GPU (Qwen, Llama). MCP server design for agentic tooling.
Senior engineering leadership for AI/automation teams without a full-time commitment. Architecture review, hiring, mentorship, on-call sanity checks. 15+ years leading engineers.
Eliminate routine tasks and connect your tools into a unified system.
Automate content, leads, and reporting for effective marketing.
Open to senior AI automation engineering roles, fractional CTO work for affiliate & iGaming teams, and consulting on production LLM & n8n architectures. Response within 48 hours.
MAIL_TO [email protected] SEND →