• Data pipeline and ETL framework in python for bringing US Govt SEC & EDGAR filings data to snowflake.
• AWS textract and REST API based processing framework for processing unstructured documents(PDFs).
• Worked on openAI text embeddings based application in FCAT.
• Intelligent Routing Algorithm which routes Fidelity's clients issues tickets to associates intelligently based on their past experience of handling tickets based on types and subtypes. It helped in reducing overall error rate by more than 30 percent in handling the tickets.
• Experience in Huggingface Sentence Transformer models for embeddings and semantic searches.
• Chat With Data feature using Langchain's csv agent where any user can upload a csv file and ask questions from their data in simple english language.
• Previously worked with People Analyticsteam and worked on multiple data engineering projects in HR domain. Projects related to compensation, hiring, attrition, re-entry, VBO program, annual employee pulse survey, workforce analytics.
• Experience in developing high quality modern data pipelines, warehousing, and reporting solutions. HR Data lake in AWS (EMR, S3,IAM, Glue, EC2) with a Curated consumption layer in Snowflake database.
• Framework for handling large volumes of un/structured data using distributed processing engine Spark and have extensive experience in Big data technologies like hadoop,hive,YARN.
• Deep understanding of AWS services and snowflake database for building data lakes in cloud
• GB Analytical Rating Engine for The Hartford Insurance, Connecticut US
• Design & Development of ETL methodology for supporting Data Migration, Data Transformations and processing in a corporate wide ETL solution.