WebRAG โ Scalable RAG Engine
High-concurrency RAG system built with Gemini-embedding-001 and Qdrant for low-latency document retrieval
Python FastAPI Celery Qdrant
+4
View Case Study
An AI/ML Engineer bridging the gap between research papers and production systems.
Machine Learning Infrastructure
LLM Optimization โข System Design
A deep dive into creating stateful AI agents that can handle complex, multi-step workflows. Here's what I learned building a production multi-agent system.