• Developed web scraping scripts using Selenium to extract data from major alcohol retailers of NSW, NT and WA, and illicit substance data from 18 major crypto markets on darknet• Performed advanced statistical data reporting and classification using Python, incorporating machine learning and deep learning techniques • Incorporated Gemini 2, Phi 3.5 and Llama 3.1 models to assist with NLP tasks and data standardisation• Co-authored the Bulletin Report and carried out documentation to present to the NSW Government

Worked remotely from Sydney, Australia.• Implemented Master Data Management (MDM) solutions for Affiliations Data, enhancing data structure and utility for Takeda• Conducted comprehensive IQVIA and CRM Affiliations data coverage analysis• Executed MDM design and build work, contributing to efficient data management strategies.• Utilized ZS REVO for setting up MDM infrastructure for ETL pre-processing and post-processing• Thoroughly tested critical MDM components, ensuring system integrity and performance.• Led the technical implementation of Business Rule Engines (BREs) using SQL, Shell, and Python scripting, enhancing operational efficiency • Spearheaded ETL operations for Abbvie on Informatica Cloud, handling clinical trials data to improve insights and decision-making in healthcare.• Developed a personalized insights system to help businesses identify potential customers using deep learning frameworks such as LSTM and SHAP, achieving 70% precision in targeting• Accelerated the Medical Legal Review (MLR) process for a pharma client by building a pipeline using Adobe and ChatGPT APIs for contextual and lexical similarity, recommending corrections for partially similar claims

Worked majorly on AWS Transition Project for Sanofi:• Engineered and tested data pipelines: Ingested data from Oracle using AWS Sqoop, AWS S3, and SFTP servers into Hive.• Leveraged Hive and Apache Spark to design Business Rules Engines (BREs) for efficient data processing and master data management (MDM) tasks.• Constructed a Shell script to optimize HDFS data storage, contributing to the project's annual cost savings of ~$50k• Developed automated file download script utilizing Shell/Python, incorporating AWS S3 Bucket and SFTP connections.

• Designed test cases to identify key scenarios, managing end-to-end test operations to validate the accuracy and reliability of datasets• Developed precise and streamlined automated test scripts leveraging Shell Script on Revo BRE, enhancing testing efficiency and accuracy• Partnered with data analysts and business analysts to rectify data inconsistencies and streamline the data processing pipeline, contributing to the overall quality of business decisions