Rishitha reddy katamareddy

About

Built and deployed a production agentic LLM knowledge assistant that answers complex questions over internal documents, APIs, and databases using a RAG architecture (FAISS/Pinecone) and LangChain/LangGraph orchestration. Emphasizes production-grade reliability and hallucination control through grounding, confidence thresholds, validation, retries/fallbacks, and full observability (logging/metrics/traces) with continuous evaluation and feedback loops.

Experience

Education

Key Strengths

• Built and deployed production agentic LLM knowledge assistant across internal docs, APIs, and databases
• Strong RAG architecture implementation with vector search (FAISS/Pinecone) for grounded answers
• Hallucination control via retrieval grounding, confidence thresholds, validation, retries, and fallbacks
• LLM workflow orchestration using LangChain/LangGraph (state management, conditional routing, long-running tasks)
• Production reliability focus: observability with logging/metrics/traces and monitoring latency and output quality
• Structured evaluation approach with success metrics (accuracy, grounding, latency, task completion) and regression testing
• Effective collaboration with non-technical stakeholders through prototypes, success metrics, and outcome-focused communication