Koushik Gunjala

About

LLM/agentic workflow engineer with healthcare domain experience who built a HIPAA-compliant multi-agent RAG system for clinical review automation at UnitedHealth Group, achieving 92% precision and cutting latency 40% through async orchestration and Redis semantic caching. Also has strong data engineering orchestration background (Airflow on AWS EMR with Great Expectations) and a proven clinician-in-the-loop feedback process that improved model faithfulness by 18%.

Experience

Education

Key Strengths

• Built and deployed agentic RAG system for clinical review automation in production
• Improved retrieval context recall by 30% and precision to 92% using hybrid search on Azure AI Search
• Reduced average response time by 40% via async orchestration, parallel execution, Redis semantic caching, and prompt/token optimization
• Designed reliability framework with modular agent unit tests, curated edge-case datasets, CI/CD regression gating, and RAGAS evaluation
• Production monitoring of latency/token usage/error rates using Azure Application Insights
• Delivered HIPAA-compliant LLM workflows in healthcare domain
• Integrated Great Expectations into Airflow DAGs to enforce data quality in large-scale AWS EMR ETL pipelines
• Effective collaboration with clinical reviewers; added citation-based explainability and feedback loop that improved faithfulness by 18%