Headline

Software Engineer @ Epsilon India | Azure Databricks | Azure Data Factory | PySpark | SQL | Data Pipelines | GenAI & AI Agents

About

I’m a Data Engineer with 4 years of experience building scalable data pipelines and cloud-based data solutions using Azure Databricks, Azure Data Factory, PySpark, Spark SQL, Python, and SQL. My experience spans the complete data engineering lifecycle — from understanding legacy data workflows and upstream/downstream dependencies to designing modern data architectures, developing transformation pipelines, validating data, and optimizing processing. In my current role, I’ve worked on customer data modernization using Medallion Architecture and Unity Catalog, building curated datasets and behavioral features to support campaign response prediction and downstream analytics. I’ve also explored the intersection of Data Engineering and Generative AI, developing an AI-driven QA validation agent using LLMs, LangChain, LangGraph, multi-agent workflows, and n8n to automate validation and human-review processes. Earlier in my career, I built a database foundation through SQL/PL-SQL development, performance tuning, ETL, automation, and data validation, including an in-house audit reporting solution that achieved 100% cost savings. I enjoy solving complex data problems, modernizing legacy processes, and building reliable solutions that turn data into something teams can actually use.

Location

Bengaluru

AI stack

claude code

claude

kiro

langchain

langgraph

openai

Work experience

Software Engineer at Epsilon India, Mar 2024 - Present · 2 yrs 9 mos, Bengaluru, Karnataka, India, Customer Data Modernization & Campaign Response Analytics *Analyzed legacy SQL/R workflows and upstream/downstream dependencies to support migration of customer data processing to Databricks. *Designed Medallion Architecture with Unity Catalog for governed customer, order, transaction, and payment data. *Migrated SQL/R transformation logic using Spark SQL and PySpark while maintaining downstream data compatibility. *Created curated customer datasets and behavioral features to support campaign response prediction and analytics. AI-Driven QA Validation Agent *Developed an AI-driven QA agent to automate validation of database changes and generated output files. *Migrated workflows from LangChain to LangGraph with conditional routing for failure handling. *Implemented LLM-based validation to identify missing/extra columns and output inconsistencies. *Integrated multi-agent validation with n8n to generate JSON reports and trigger review workflows.

Associate Software Engineer at Epsilon India, Aug 2022 - Mar 2024 · 1 yr 8 mos, Bengaluru, Karnataka, India, *Designed and implemented an in-house audit reporting system using PL/SQL, SQL, batch scripting, and Python, eliminating third-party dependency and achieving 100% cost savings. *Developed high-performance SQL and PL/SQL solutions using joins, bulk operations, constraints, and optimized data-processing logic for transactional systems. *Automated ticket-management activities using Selenium and Python, enabling accurate priority flagging and timely escalations with email alert. *Improved query execution by 25% through advanced SQL optimization techniques including hints, analytic functions, and index management. *Worked with SSIS, SnapLogic, and REST APIs to support application workflows and enterprise data integration. *Performed code reviews and maintained technical documentation, following Git-based development.

Intern at Epsilon India, Jan 2022 - Jul 2022 · 7 mos, Bengaluru, Karnataka, India

Education

Bachelor of Engineering - BE, Electronic and communication engineering, CMR Institute Of Technology

12, Science, Delhi public school