AI-focused backend engineer building scalable LLM-powered systems, vector retrieval pipelines, and high-performance data platforms.
I treat systems as long-term infrastructure assets - prioritizing reliability, observability, and performance. My work spans architecture design, RAG pipeline implementation, async processing optimization, API-first development, and containerized deployment.
Strong focus on performance-aware backend design and failure-resilient systems.
Production-ready LLM integration into backend systems
Scalable data & RAG pipelines powered by vector search
Async & concurrent architectures with measurable performance gains
Fault-tolerant web data acquisition systems (<1% failure rate)
API-first backend services ready for product integration
From architecture to deployment - full lifecycle ownership
Python · FastAPI · PostgreSQL · MongoDB · REST APIs
LLM Integration · RAG Pipelines · pgvector · Embeddings · Prompt Engineering
Asyncio · Multiprocessing · Concurrency Patterns · High-Load Backend Design
Docker · Linux · Git · Containerized Deployment
Playwright · Selenium · Proxy Rotation · Anti-bot Strategies
Typical production-grade AI backend architecture combining async ingestion, vector search, and LLM-powered retrieval.
Async pipelines · API ingestion · Structured data validation
OpenAI embeddings · pgvector · Indexed similarity search
Semantic search · Context assembly · Scored ranking
RAG pipeline · Prompt engineering · Controlled generation
FastAPI backend · JSON response · Containerized deployment
Designed and implemented a production-ready AI-driven retrieval system combining structured data ingestion, vector embeddings, and semantic search. The solution enables efficient similarity-based retrieval and serves as a foundation for retrieval-augmented generation (RAG) workflows.
View DetailsDesigned and implemented a resilient high-volume data acquisition system with a FastAPI-based backend layer for structured data delivery. The system operated under advanced anti-bot constraints while exposing clean, programmatic access to normalized datasets.
View DetailsArchitected a high-throughput data ingestion system aggregating structured records from multiple dynamic platforms. The system ensures consistent normalization, incremental updates, and reliable downstream delivery.
View DetailsBuilt multiple production-grade AI & backend systems
Designed AI-ready data architectures supporting semantic search and intelligent retrieval
Optimized processing throughput by up to 8×
Maintained <1% failure rate in large-scale extraction pipelines
Delivered full-cycle systems from architecture to deployment
Designed scalable data systems processing tens of thousands of records
Open to remote roles across EU & US markets.
AI Backend Engineer · LLM Systems Engineer · RAG & Vector Search Architect