Prathima S

About Prathima S

I’m an AI/ML Data Engineer with 4 years of experience turning raw data into intelligent, scalable systems. I work with modern cloud technologies to ensure data is reliable, secure, and fully optimized for machine learning and automation. I have strong experience in data engineering, building distributed ETL/ELT pipelines using PySpark, Databricks, AWS Glue, Snowflake, and Airflow. I design efficient data lakes and warehouses that support analytics, automation, and real-time decisions. On the AI side, I build Generative AI and LLM-powered workflows, including RAG systems, embeddings search, and prompt engineering using OpenAI, FAISS, and Pinecone. I also automate ML operations with SageMaker, Step Functions, and MLflow. I’m passionate about creating platforms where data, AI, and automation work together to improve efficiency, unlock knowledge, and drive smarter decisions across organizations.

Experience

1. Ai Ml Data Engineer

   Truist

   Jul 2024 — Present · US

   Designed and developed Retrieval-Augmented Generation (RAG) frameworks using LLMs, FAISS, and Pinecone, enabling semantic document search, summarization, and compliance policy Q&A-Built Generative AI pipelines leveraging OpenAI APIs and integrated with Azure OpenAI Service for automated report generation, policy interpretation, and knowledge retrieval across enterprise systems- Developed AI-ready data pipelines using PySpark, Python, and AWS Glue, processing large volumes of structured and unstructured data to support analytics and ML workflows-Architected and maintained data lake environments on AWS S3 and Redshift, with limited integrations into Azure Data Lake Storage (ADLS) for cross-platform data sharing and archival-Automated ML model retraining and inference workflows using AWS SageMaker, Step Functions, and MLflow, improving deployment efficiency and ensuring reproducibility across environments-Designed and implemented data monitoring dashboards using CloudWatch and QuickSight, tracking pipeline health, data drift, and SLA compliance, improving reliability by 20%-Applied data governance and security best practices using AWS IAM, KMS, and Glue Data Catalog, with Azure Key Vault for key management interoperability and compliance-Optimized ETL job performance and AWS resource utilization, achieving a 30% reduction in compute costs across production pipelines- Optimized end-to-end AI/ML data pipelines for scalability and reliability, improving model deployment speed and reducing overall data processing latency by 25%.

Education

• University of North Texas

  Master's

  2023 — 2024

• Bhashyam College of Education (BCE), Guntur

  SSE

  2015 — 2016

• Vignan's Lara Institute of Technology & Science, Vadlamudi, Chebrolu Mandal, PIN-522213(CC-FE)

  Bachelor of Technology - BTech

  2018 — 2022