Backend Engineer specializing in building scalable systems and LLMOps pipelines. I bridge the gap between heavy-duty backend infrastructure (Node.js/FastAPI) and AI production environments, focusing on RAG (Retrieval-Augmented Generation), Vector Search, and high-performance database management.

• LLMOps: Deploying and monitoring RAG pipelines and vector search indices.
• Search Optimization: Implementing Semantic & Hybrid search using ElasticSearch and Vector Databases.
• Infrastructure: Managing production environments on Linux VPS using Nginx and PM2.

• Advanced Backend: Scalable API design, Microservices, and Large-scale Data Migration.
• AI Infrastructure: Vector Embeddings, Chunking strategies, and Prompt Engineering.
• DevOps: Linux hardening, Bash scripting, and Nginx reverse proxies.

• LinkedIn: Rafshan Jani
• Email: rafshan.dev@gmail.com

• 🧠 Production RAG Pipelines: Built end-to-end LLM applications with custom vector store integrations.
• 🚀 398GB+ MongoDB Migration: Engineered a high-performance data import strategy for production-grade datasets. View Repo
• 🌐 VPS Infrastructure: Designed and deployed scalable Nginx/PM2 environments for FastAPI/Node.js services.

"Simplicity is the soul of efficiency."