Priyanka Mamillapalli

About Priyanka Mamillapalli

Over the years, I’ve worked across multiple domains delivering AI-driven, data-intensive, and cloud-based solutions that combine full-stack engineering with advanced machine learning and generative AI. My career began in application and data support, where I managed ETL pipelines, automated workflows, and optimized SQL-based data systems. As I transitioned into data engineering, I built and modernized large-scale data pipelines using Kafka, PySpark, and Azure Data Factory, enabling real-time analytics and insights. I also developed and deployed machine learning models for predictive analytics, recommendation systems, and anomaly detection using tools such as TensorFlow, Scikit-learn, and XGBoost. My work has spanned several Fortune 500 companies, where I contributed to end-to-end AI transformations. At Goldman Sachs and Verizon, I built enterprise AI/ML platforms integrating NLP models, RAG frameworks, and compliance-driven analytics on AWS and Azure. At Abbott Laboratories, I led the development of a Generative AI platform that automated financial analysis and compliance intelligence using LLMs, LangChain, Pinecone, and FastAPI. I’ve deployed scalable AI services using Docker and Kubernetes, implemented Responsible AI practices for data governance, and optimized MLOps pipelines with MLflow, Kubeflow, and GitHub Actions. My work also included building visualization dashboards with Power BI and Tableau to make AI insights accessible to business teams. My focus has always been on building practical, scalable, and ethical AI solutions that combine innovation, automation, and data intelligence to drive measurable business impact.

Experience

1. Gen Ai Engineer

   Abbott

   Mar 2024 — Present · Abbott Park, IL, US

   Spearheaded the development of Generative AI applications for financial reporting, risk assessment, and compliance automation. • Built LLM-powered systems using GPT-4, Claude, and LLaMA 3 for intelligent document summarization. • Managed MLOps pipelines with MLflow and Airflow, ensuring smooth model retraining and version control. • Partnered with finance and compliance teams to align AI solutions with regulatory needs, enhancing operational efficiency.