Bhavishyasai Chigurupati

About

Built and productionized an LLM-based financial document analysis system using a RAG pipeline, including robust ingestion/chunking/embedding workflows, vector DB retrieval, and an AWS-deployed FastAPI service containerized with Docker. Demonstrates strong applied expertise in improving retrieval quality and latency at scale, plus hands-on experience debugging agentic/LLM workflows with monitoring and trace-based analysis while supporting demos and customer-facing adoption.

Key Strengths

• Took an LLM/RAG document analysis prototype to production on AWS (FastAPI + Docker)
• Improved RAG retrieval accuracy via chunking changes, metadata filtering, and similarity threshold tuning
• Scaled performance for large document volumes by optimizing top-k retrieval and precomputing embeddings to reduce latency
• Systematic real-time debugging of LLM/agent workflows using metrics (relevance, latency, token usage, error rate) and trace inspection
• Strong technical communication: delivers end-to-end demos/workshops focused on architecture, data flow, and implementation details
• Partners with customer-facing teams to translate technical architecture into business outcomes and drive adoption

Experience

Education

Skills

Languages