Backend & AI/LLM Engineer

I build high-load distributed systems and production AI platforms. Currently focused on LLM-powered applications, RAG pipelines, and intelligent automation.

• Design and build production AI/LLM systems (OpenAI, Gemini, RAG, LangChain)
• Architect high-load Python backends (FastAPI, Django, Celery, asyncio)
• Build Telegram bots and business automation platforms
• Integrate payment systems, CRMs, and third-party APIs
• Mentor Python developers (10+ students, from zero to job-ready)

Production-ready RAG chatbot API — upload documents, ask questions, get AI-powered answers with source citations. FastAPI OpenAI ChromaDB PostgreSQL Docker Pydantic v2

Lead distribution microservice with weighted routing, workload balancing, and multi-source support. FastAPI SQLAlchemy 2.x Pydantic v2 Docker Alembic

Python     FastAPI    Django     Celery     asyncio    Pydantic
PostgreSQL Redis      MongoDB    DynamoDB   ChromaDB   SQLAlchemy
OpenAI API LangChain  RAG        GPT-4      Embeddings Prompt Eng.
AWS        Docker     Kubernetes CI/CD      Nginx      Linux
Pytest     Playwright Selenium   RabbitMQ   WebSockets SSE

• AI Career Assistant — LLM-powered chatbot (FastAPI + OpenAI + RAG + Celery), 50K+ MAU
• LLM Platform — AI agent orchestration, RAG pipelines, streaming responses
• Business Automation — CRM integrations, Telegram mini-apps, automated reporting
• VPN Service — Payment processing (Stripe, crypto), 10K+ concurrent connections