Tejaswi Kothapalli

About

Built a production RAG-based GenAI copilot backend at Aetna using Python/FastAPI, GPT-4, LangChain, and Azure AI Search, deployed on AKS with Prometheus/Grafana observability. Owned the system end-to-end (ingestion through deployment) and improved peak-time reliability by addressing vector search and embedding bottlenecks with Redis caching, index optimization, and async processing, plus added anti-hallucination guardrails via retrieval confidence thresholds.

Key Strengths

• Built and deployed production GenAI/RAG backend services on Azure (FastAPI, AKS) for enterprise copilots
• End-to-end ownership: document ingestion, embedding pipeline, vector search + GPT-4 integration, and production deployment
• Diagnosed and reduced peak latency/timeouts via Redis embedding cache, vector index optimization, and async FastAPI pipeline
• Designed multi-agent workflows (planner/executor/verifier) with robust error classification, retries/backoff, and fallback tools
• Implemented LLM guardrails to prevent hallucinations using confidence thresholds and retrieval validation
• Strong production engineering practices: layered architecture, Pydantic validation, typed models, testing + CI/CD, and observability
• Designed PostgreSQL schemas with constraints/migrations and improved slow queries via indexing and query rewrites

Experience

Education

Skills

Languages