Pavan Kalyan Natukula

Data Engineer with 3+ years of experience building scalable, cloud-native ETL pipelines on Google Cloud using Dataflow, BigQuery, Pub/Sub, Datastream, Apache Beam, and PySpark to deliver analytics-ready and near real-time data. I also work at the intersection of Data Engineering and AI, developing RAG and LLM-powered applications using LlamaIndex, LangChain, ChromaDB, and FastAPI to automate document processing and knowledge retrieval. My work has helped significantly reduce manual effort and accelerate decision-making. Previously at Cognizant, I designed end-to-end GCP data pipelines processing 10M+ records, built EDW models using SCD Type 2, and orchestrated workflows with Cloud Composer (Airflow) while optimizing performance and cost. Completed my Master’s in Data Science (GPA: 4.0) at University of North Texas and actively seeking opportunities in Data Engineering and AI Engineering. Skills: Data Engineering: BigQuery, Dataflow, DataStream, Pub/Sub, Cloud Storage, Cloud Composer Cloud & Big Data: AWS Cloud, Google Cloud Platform, Apache PySpark, Apache Beam, Apache Airflow AI & ML: TensorFlow, Keras, Scikit-Learn, LlamaIndex, Retrieval Augmented Generation, ChromaDB, Ollama, AI Agents. Databases: Oracle DB 19C, Microsoft SQL Server, PostgreSQL. Languages: Python (Pandas, NumPy, Matplotlib,), SQL, PL/SQL. Automation & CI/CD: Git, GitHub Actions, N8N