Building a Retrieval-Augmented QA Chatbot
Building a QA chatbot with memory using Langchain, Faiss, Streamlit and OpenAI (Retrieval-Augmented Generation (RAG)).
Data Engineer | BI & Analytics
Building scalable data pipelines and analytics platforms that turn data into decisions.
I’m Jeevaharan, a data professional with 4 years of experience building scalable data platforms and analytics solutions across industrial, supply chain, financial services, and healthcare domains. My work focuses on data engineering and cloud-based systems, where I’ve designed high-performance data pipelines, orchestrated complex workflows, and supported large-scale migrations from on-premises systems to cloud platforms such as AWS, Azure and Snowflake.
I’ve also worked on generative AI and LLM-based proof of concepts, building chatbot and AI-driven solutions that integrate with enterprise data systems. I hold a Master’s degree in Data Science from the University at Buffalo (SUNY), with a strong foundation in statistical data mining, machine learning, and data-intensive computing.
I enjoy building reliable, maintainable data systems and collaborating with teams to solve real-world problems at scale.
Aug 2024 - Dec 2025 | CGPA - 4.0/4.0
Coursework: Data Intensive Computing, Statistical Data Mining, Machine Learning, Probability and Data Analysis.
Aug 2017 - June 2021 | CGPA - 8.89/10
Coursework: Problem Solving and Python Programming, Microprocessors and Microcontrollers, Introduction to C Programming, Object Oriented Programming.
Recognized for successfully designing and implementing robust and performance-optimized ETL pipelines, supporting critical business reports and decisions.
Recognized for outstanding team collaboration and successful migration from Cloudera Hadoop to an AWS-based Snowflake solution, delivering significant cost savings.