Ajay Kumar Devireddy

About

ML/AI engineer with healthcare payer experience (Signal Healthcare, Cigna) who has shipped production fraud/claims prediction systems using Python/TensorFlow and exposed them via FastAPI/Flask microservices integrated with EHR and Salesforce. Emphasizes operational reliability and trust—Airflow-orchestrated pipelines with data quality gates plus SHAP-based interpretability, A/B testing, and drift/debug workflows—backed by reported outcomes of 22% lower false payouts and 17% higher model accuracy.

Experience

Education

Key Strengths

• Deployed healthcare fraud/claims prediction ML models to production with measurable impact (22% reduction in false claim payouts; +17% accuracy)
• Production ML serving via FastAPI/Flask microservices with low-latency integrations (EHR, Salesforce, analytics dashboards)
• Strong focus on model reliability and governance: A/B testing, SHAP interpretability, and error diagnosis to build stakeholder trust and support compliance
• End-to-end ML pipeline orchestration with Airflow (DAG dependencies, retries, backfills, conditional execution, data quality gates) to reduce manual intervention
• Practical approach to debugging and monitoring (interpretability-driven root cause analysis; data drift awareness)
• Effective collaboration with non-technical stakeholders (ops/compliance) through explainable outputs, dashboards, and workshops