Akshay Amudhan

About

Built and deployed a production RAG chatbot using a vector database + LangChain-orchestrated pipeline, focusing on grounded, context-aware responses. Demonstrates practical trade-off thinking (retrieval quality vs latency/cost), hallucination control, and iterative improvement through logging, manual review, and stakeholder feedback loops.

Experience

Key Strengths

• Built and deployed a production RAG chatbot end-to-end (ingestion → embedding/indexing → retrieval → LLM generation)
• Balances retrieval quality vs latency via chunk-size tuning, retrieval-depth limits, and constraining LLM context
• Iterative post-deployment optimization using latency checks and manual answer review
• Designs modular, testable AI workflows with clear stage boundaries to improve debuggability and reliability
• Uses logging/tracing of inputs, retrieved context, and outputs to diagnose failures and improve performance
• Effectively translates stakeholder needs into usable outputs and iterates based on non-technical feedback