Dec 2023 – Apr 2024 · 4 mos

Aug 2021 – Dec 2023 · 2 yrs 4 mos

• Patient level data analytics - Molecular diagnosis pharma company
• Technologies : Databricks , pyspark , SQL , Snowflake
• Orchestrated a data model to encompass a dynamic and versatile analytical environment.
• Built a process to retrieve continuously enrolled patient episodes.
• Built highly configurable notebooks as per the client requirements to identify patients which are susceptible to screening of Colorectal Cancer
• Data ingestion adaptor - ZS internal asset
• Technologies : pyspark, AWS EMR , AWS EC2 , AWS Athena
• Operationalized existing ingestion framework with open source clinical trials data - Pubmed, AACT.
• Developed add on utilities to accompany requirements of the broader team.
• Evidence explorer - ZS internal asset
• Technologies : Azure Functions , python , API development
• Developed Backend APIs on top of the data science code.
• Collaborated with data science team to create a research prototype.
• Worked on technical feasibility to onboard future data sources and planned a walkthrough of various data sets which can be leveraged in the future.
• Access management platform - Global biopharma company
• Technologies - Denodo (data virtualization), Databricks , API Integration, Azure ADLS
• Developed workflows to identify the delta users within the client environment who need access to various clinical applications based on their roles in clinical studies.
• Reduced the application access cycle time from 3 Months to few days by automating the manual process of approval.
• Collaborated with multiple source data teams to leverage the concept of data virtualization optimally.