Implemented predictive analytics to develop two key components, namely maintenance ability & latency, for an optimization model that is aimed at enhancing the operational flexibility of aircraft maintenance while reducing cash-flows.
Streamlined the data-pipeline by logic optimization in order to reduce the model's computational time from 3 hours to 30–45 minutes.
Aided the release of the return-to-service optimization model V1 for the line maintenance engineers.
Collaborated and maintained a source control, Python-coded, environment with data analysts, data scientists, and data engineers.
Developed proficiency in programming languages (PySpark, Python).
Worked on the Palantir Foundry and utilized its functionalities related to data integration and computing.
