Meghana P

About

AI/ML engineer with forensic analytics and healthcare claims experience (Optum), building production LLM/RAG systems to surface context-driven fraud patterns from unstructured claim notes and explain risk to investigators. Strong in large-scale retrieval performance tuning, legacy API integration with reliability patterns (SQS, circuit breakers), and MLOps orchestration on Airflow/Kubernetes with rigorous testing, monitoring, and stakeholder-friendly interpretability.

Experience

Education

Key Strengths

• Built and deployed production RAG/LLM system for fraud detection using unstructured claim notes
• Performance optimization at scale (sub-second retrieval over millions of embeddings via ANN tuning, vector quantization, caching)
• Robust integration into legacy ecosystems (schema contracts via OpenAPI, SQS-based async handling, retries, circuit breakers)
• Security-minded handling of PII (JWT auth, AWS Secrets Manager credential rotation)
• End-to-end MLOps orchestration with Airflow DAGs (data ingestion through deployment, quality gates, automated alerts)
• Kubernetes-based microservices deployment with Helm and autoscaling
• Strong evaluation and reliability practices (unit/integration tests, shadow deployments, A/B tests, monitoring/rollback with Prometheus/Grafana)
• Effective collaboration with non-technical stakeholders to translate workflows into model features and deliver interpretable dashboards