Balakrishna Mylapilli

About

ML practitioner who built a production customer risk scoring system to replace slow manual approvals, owning the full pipeline from feature engineering and XGBoost training to deploying a Dockerized FastAPI prediction service. Emphasizes reliability and business-aligned evaluation (recall/ROC-AUC, threshold tuning, drift monitoring) and is comfortable translating model decisions into stakeholder metrics like conversion rate (experience at EasyBee AI).

Experience

Education

Key Strengths

• Built and deployed an end-to-end production risk scoring system (data prep → modeling → API deployment)
• Production deployment experience with Dockerized FastAPI real-time inference service
• Strong handling of imbalanced classification (stratified CV, class weighting, SMOTE experimentation, threshold tuning)
• Metric-driven model evaluation aligned to business goals (recall/ROC-AUC over accuracy)
• Experiment tracking and reproducibility using MLflow
• Reliability mindset: edge-case testing, A/B testing, post-deploy monitoring for drift
• Effective communication with non-technical stakeholders by translating model changes into business impact (e.g., conversion vs risk tradeoffs)