- Responsible for implementing and scaling bioinformatics algorithms and data pipelines that predict genetic insights like ethnicity, traits and matches for tens of millions of customers on the cloud (AWS) each year. - Built data pipelines using AWS Lambda, SQS, ECS and Step Functions. - Led the backend engineering effort to scale the new Ethnicity Inheritance algorithm on 22 million customers. This engineering effort was the first-of-its-kind in the consumer-genomics industry and a patent has been filed. - Helped build new PRS trait models (using Logistic Regression) and reduce the time to productionize from a month to a few days.- Implemented statistical checks (using Z-score) to catch anomalies and ensure accuracy of results.- Worked on designing a new API Gateway and SDK for 40 internal teams using Netflix’s Zuul service and RXJava

- Implemented a pipeline in Java (Spring Boot) which reduced the time to extract insights, by performing Genome Wide Association Studies (GWAS) on Ancestry’s 5 million-strong DNA database, from 1 week to a few hours. - This also helped increase the security of data access and make the research process for scientists more seamless.

- Successfully implemented a pipeline in Python in the Biomolecular Computation lab of Dr. Debnath Pal that ascertains the statistical significance of of tens of thousands of protein-protein docking predictions. - Estimated how much better/worse than random some docking/ ranking algorithms were.