Lakshmi Pulicharla

Designed and deployed AI and machine learning solutions for banking use cases including transaction monitoring, fraud investigation, and regulatory reporting using Python-based ML and deep learning models. Built, trained, and deployed models using AWS SageMaker, supporting batch and near real-time risk scoring workflows across large-scale transactional datasets. Containerized ML and inference services with Docker, and provisioned cloud infrastructure using Terraform. Implemented CI/CD pipelines for ML workflows, integrated SageMaker endpoints with Lambda for event-driven decisioning, and established monitoring and logging for reliability and governance in regulated environments. Applied statistical analysis and model evaluation to tune thresholds and monitor behavior over time.

Designed and developed machine learning and NLP models for healthcare use cases such as patient risk stratification, readmission prediction, and clinical decision support using Python and scikit-learn. Built deep learning models (LSTM, CNN) for structured and unstructured EHR data, and developed AI-driven conversational and summarization solutions for secure EHR querying. Curated healthcare datasets on Azure, implemented NLP pipelines for clinical entity extraction with spaCy and transformers, and established CI/CD on Azure Databricks with MLflow for reproducible experiments. Automated retraining and deployment workflows with Apache Airflow and Kafka-based data ingestion.

Developed and productionized ML models for banking use cases including credit risk assessment, fraud detection, and customer analytics. Built end-to-end Python pipelines for data preparation, training, validation, and batch inference; implemented RESTful inference services via Flask; integrated CI/CD pipelines for automated testing and deployment with versioning and rollback. Implemented monitoring and logging to track model execution and data drift, and collaborated with compliance teams to ensure governance and audit readiness.