AI Integration Engineer · stock.link

Rusu
George

Production agentic AI
for enterprise manufacturers

Enterprise RPA veteran now shipping production agentic AI — agentic pipelines, LLM decision layers, and Human-in-the-Loop approvals running in real manufacturer operations.

// current_projects

What I'm Building Now

Chapter I · Shipped

Agentic AI Playground

LangGraph × Qdrant × Langfuse

My working lab for agentic patterns — LangGraph orchestration, hybrid retrieval on Qdrant, and full Langfuse observability. The four years I spent shipping enterprise RPA in production are exactly what make these agents reliable: I build for the constraints of real operations, not just the happy path.

n8n LangGraph LangChain FastAPI Gradio Qdrant Langfuse
Started: March 2026 · Status: Shipped
View on GitHub

Chapters

Chapter I

Playground

LangGraph n8n Langfuse Qdrant
Shipped

Chapter II

AI On-Call

Twilio ITSM Redis
Pilot Case

Chapter III

RAG Service

Qdrant FastAPI Langfuse Redis
Shipped

Chapter V

???

Coming next…

// always building

Chapter II · Pilot Case

AI On-Call — Voice Agent for IT Support

Twilio × LangGraph × ITSM

Outbound voice AI that fires when a ITSM ticket opens. The agent calls the customer, verifies identity via 6-digit user code, collects a work note and ETA, then pushes everything back through n8n into ITSM — zero human dispatcher needed.

Twilio LangGraph n8n FastAPI ITSM Redis Langfuse
Shipped: April 2026 · Status: Pilot Case
View on GitHub
Chapter III · Shipped

Production RAG Service — Hybrid Search API

FastAPI × Qdrant × Redis × Langfuse

A production-grade, multi-tenant RAG API built from first principles — implementing the full 2026 RAG stack that industry leaders deploy at scale. Hybrid dense+sparse search with RRF fusion, cross-encoder reranking sidecar, async ingest queue with DLQ, streaming SSE answers, namespace-scoped RBAC, Prometheus metrics, and per-stage Langfuse tracing. 13 file formats including audio via Whisper.

// 2026 rag stack

Hybrid Dense+Sparse (RRF) Cross-Encoder Reranking Async Queue + DLQ Streaming SSE Answers Namespace RBAC + JWT Prometheus + Langfuse
Qdrant FastAPI Redis Langfuse OpenAI Hybrid Search Pydantic v2 Docker
Shipped: April 2026 · Status: Shipped
View on GitHub
Chapter IV · Live

Agent Orchestrator — Multi-Agent AI System

LangGraph × Groq × FastAPI × ChromaDB × SSE

A live multi-agent system deployed on Hugging Face Spaces. A LangGraph orchestrator routes each visitor request to the right specialist: RAG for questions about my background, Email to send the CV, Calendar to book a Google Meet, Job Match to score JD fit, and Telegram for instant notifications. Every routing decision streams live to the UI via SSE.

// agents_active

RAG — knowledge Q&A Email — sends CV via Gmail Calendar — books Google Meet Job Match — JD fit score Telegram — notifications
LangGraph FastAPI Groq ChromaDB SSE Streaming Docker · HF Spaces
Started: May 2026 · Status: Live
Talk to the Agent

Open Source

All public projects — github.com/georgelush

YouTube

Project demos & walkthroughs

Technical Foundations & Legacy Projects

Cybersecurity labs, RPA automation, Unreal Engine 5 prototypes, and C++ systems — the technical depth behind the production agentic systems I ship today.

Explore Archive
Lush AI