Rohith Gaddam

I’m a results-driven Data Engineer with 1+ year of experience building scalable data pipelines and RAG-based AI systems at HSBC. I focus on turning complex data workloads into reliable, production-ready workflows.

I architected and deployed end-to-end Apache Spark data processing pipelines on GCP Dataproc for large-scale batch processing. I also designed and built a Retrieval-Augmented Generation (RAG) pipeline using encoder-decoder transformer models to extract structured information from unstructured enterprise documents.

I orchestrate multi-step data workflows using Apache Airflow to deliver dependable scheduling, monitoring, and alerting across production pipelines. I’ve also implemented CI/CD pipelines using Jenkins to automate build, test, and deployment and improve pipeline reliability.

I enjoy working at the intersection of data engineering and machine learning, especially in fast-paced startup environments. My projects range from a locally deployed LLaMA 3.1 role-based chatbot (with a REST API) to a Flask-based movie recommendation system using TF-IDF and cosine similarity, along with hands-on Flutter UI work.