Senior AI Data Engineer at First Citizens Bank

Designed enterprise-scale Generative AI solutions on Google Cloud Platform, leveraging OpenAI, Claude models, LangChain, LlamaIndex, and vector databases to support financial intelligence, compliance automation, and risk management. Implemented Retrieval-Augmented Generation with Pinecone, Weaviate, and FAISS to ground LLMs using internal policies and regulatory documents. Built multi-agent AI systems using AutoGen, LangGraph, and LangChain to automate financial investigations, compliance workflows, intelligent document processing, and operational decision support. Architected Claude-powered coding and workflow automation for enterprise knowledge management and intelligent task orchestration. Established AI orchestration layers enabling secure communication between LLMs, enterprise tools, vector databases, and external knowledge sources. Built scalable vector embedding pipelines for semantic retrieval and contextual reasoning. Implemented AI-powered compliance monitoring using LLMs and

Senior Data AI/ML Engineer at Siemens Healthineers

Designed AI-driven clinical intelligence and medical imaging platforms on AWS and Azure, integrating Generative AI, medical imaging analytics, and enterprise knowledge management. Built Retrieval-Augmented Generation frameworks with OpenAI models, LangChain, vector databases, and clinical knowledge repositories to support physician decision-making and automated report generation. Developed multi-agent AI workflows for clinical document processing, medical coding assistance, and healthcare operations. Implemented Semantic Kernel-based healthcare assistants to orchestrate AI services and clinical APIs; designed vector search across notes, imaging reports, and research repositories. Established HIPAA-aligned governance, secure AI deployment practices, and observability for model drift and retrieval quality. Built real-time AI inference pipelines and GPU-accelerated deployments.

Senior Data ML Engineer at Foot Locker

Implemented Real-Time Retail Fraud Detection system using Python, Spark, Kafka, and ML pipelines to enable instant anomaly detection on transaction streams. Built streaming architecture with Kafka and Spark Streaming on AWS; developed fraud models (XGBoost, Random Forest) and real-time feature pipelines with PySpark, AWS Glue, and Airflow. Led end-to-end ML lifecycle with MLflow and CI/CD; designed anomaly detection and time-series analytics for fraud signals. Created customer intelligence engine for segmentation of high-risk and high-value customers; exposed real-time inference APIs via FastAPI. Implemented end-to-end data processing on Spark/Delta Lake with S3 storage; built dashboards with Tableau/Power BI; optimized inference with ONNX/TensorRT; built event-driven processing via Kafka Streams and AWS Lambda.

Python Big Data Engineer at Allstate

Designed and developed an enterprise-grade Insurance Claims Risk Modeling & Compliance Intelligence Platform using Python, PySpark, and Spark to process high-volume claims for risk scoring and fraud detection. Built Hadoop/Spark pipelines, developed risk models (scikit-learn, XGBoost), automated ETL with Airflow, and governance for compliance. Implemented real-time streaming ingestion with Kafka and Spark Streaming; built data lake on HDFS; deployed ML pipelines with Spark MLlib; created dashboards for compliance officers; collaborated with actuarial and compliance teams to align data-driven risk insights with governance.