Six (6) years of experience must include: Designing, developing, and maintaining ETL workflows using the Ab Initio ETL Suite, and implementing distributed data processing solutions using Apache Spark / PySpark and Hadoop ecosystem tools (Hive, HDFS, YARN); Developing and supporting production grade applications and data pipelines using Python and Java, and writing complex SQL and PL/SQL queries for relational databases such as Oracle; Developing, training, and validating machine learning and deep learning models using frameworks including, TensorFlow, PyTorch, and Scikit learn, including applying Natural Language Processing techniques; Designing and implementing solutions leveraging Large Language Models (LLMs), including prompt engineering and Retrieval Augmented Generation (RAG) architectures; Building and supporting real time data pipelines using Apache Kafka and developing RESTful APIs for system integration; and Managing source code using distributed version control systems and tracking development tasks using issue tracking tools. Develop high performance, automated data and machine learning pipelines using big data frameworks to ingest, transform, and validate large volumes of structured and unstructured data from diverse sources.