• Designed an enterprise RAG platform combining semantic retrieval and LLM reasoning, accelerating fraud investigations by 40% for 50+ analysts.

• Architected scalable RAG pipelines using FAISS, Pinecone, and ChromaDB, enabling sub second search across large financial document repositories.

• Developed agentic AI workflows using LangChain and LangGraph to automate multi step reasoning for fraud policy analysis.

• Enhanced fraud narrative classification accuracy by 17-20% through BERT fine tuning with LoRA and zero-shot classification techniques.

• Reduced fraud false positives by 18% by building ensemble risk models using XGBoost, Random Forest, and LightGBM.

• Implemented near real time credit risk scoring pipelines integrating transaction and bureau data.

• Deployed anomaly detection models using Isolation Forest to strengthen AML monitoring and detect suspicious activity.

• Automated large scale ETL pipelines using Apache Spark, AWS Glue, and S3 to process multi terabyte financial datasets.

• Operationalized ML services using FastAPI microservices, Docker containers, MLflow, and CI/CD pipelines.

• Integrated model monitoring and explainability frameworks using SHAP and LIME to support regulatory compliance.

• Created clinical prediction models for patient readmission and treatment outcomes, improving model performance by 14%.

• Engineered scalable healthcare data pipelines using Azure Data Factory, Databricks, and PySpark to process large EHR datasets.

• Constructed NLP pipelines extracting medical entities from physician notes, reducing manual chart review by 30%.

• Designed time series forecasting models (ARIMA, SARIMA) for hospital capacity planning.

• Built semantic search systems using FAISS to enable fast retrieval across medical knowledge bases.

• Deployed deep learning models using PyTorch on Azure Kubernetes Service, reducing inference latency by 25%.

• Streamlined ML lifecycle management using Azure Machine Learning for experiment tracking and deployment.

• Led development of a retail analytics platform integrating demand forecasting, inventory optimization, and personalization models.

• Improved demand forecast accuracy by 31% using XGBoost, LightGBM, and TensorFlow.

• Developed recommendation systems increasing customer engagement by 11-14%.

• Established scalable ETL workflows using AWS Glue, Apache Spark, Databricks, and Airflow.

• Applied NLP techniques to analyze customer sentiment and product reviews, reducing processing time by 35%.

• Delivered business insights through Tableau and Power BI dashboards for merchandising and supply chain teams.