Data Analyst
- Deployed a RAG model on Databricks for data extraction from pdf utilising MLFlow to manage the model lifecycle. Implemented meta-data filtering to allow on-request filtering of chunks enabling querying of insights. Improved extraction speed from hours to instant.- Performed web scraping using Selenium and Beautiful Soup, deploying scripts on AWS Lambda to upload data to an S3 bucket. Automated job runs through AWS EventBridge, integrating with an AWS ETL pipeline.