Ramya Konda

About

AI/LLM engineer at Humana who built and deployed a HIPAA-aware RAG system for clinical record retrieval, cutting search time dramatically and improving retrieval efficiency by 30%. Experienced with Spark-scale data preprocessing, QLoRA fine-tuning, LangChain orchestration, and MLflow+SageMaker integration, with a strong testing/evaluation discipline (A/B tests, human eval) to hit 95%+ accuracy and production latency targets.

Experience

Education

Key Strengths

• Built and deployed production RAG pipeline for clinical data retrieval at Humana
• Improved data retrieval efficiency by 30% for healthcare professionals
• Scaled preprocessing with Apache Spark, reducing processing time by 40%
• Efficient LLM fine-tuning using QLoRA for customization under performance constraints
• Designed modular agent/workflow architecture (retrieval, context processing, generation) with LangChain
• Implemented multi-level testing (unit/integration/e2e) plus A/B testing before rollout
• Established measurable evaluation (retrieval relevance, human-rated accuracy) achieving 95%+ accuracy while meeting latency requirements
• Integrated MLflow with AWS SageMaker in a HIPAA-compliant environment
• Strong cross-functional collaboration with clinical operations; incorporated feedback (citations, faster responses) and communicated impact via business metrics