Worked in CLAIRE(AI) team to make Informatica products robust and develop a centralized data lake with analytics-ready data to power Informatica’s analytical and AI use cases.Worked on profiling metadata from different sources and Implementation of scanner system for stand-alone data extraction. Performed data extraction via APIs from different INFA products.

Worked on Jenkins, docker, and Informatica PowerCenter to create a PowerCenter server setup on docker and created a server utility service on Linux Machine.Developed pipeline design and building of E2E for POC the project. Stored extracted metadata to develop a functioning prototype for the POC of the project.Worked on model training and dataset refining for similar terms project. Prepared rule building strategies to achieve 97% accuracy across all datasets.