Sonia Malik Email & Phone Number

Mountain View, California, United States

* Developing advanced machine learning and deep learning models, to enhance customer interaction and product features for TurboTax.* Utilized Natural Language Processing (NLP) techniques including sentiment analysis and topic modeling, alongside Generative AI (GenAI) and language models, to analyze TurboTax customer reviews and extract actionable insights to optimize product experience.* Leading end-to-end deployment of the developed ML models ensuring seamless integration within the product. * Collaborate closely with cross-functional teams to translate business requirements into machine learning solutions, thereby improving product functionality and user experience through data-driven insights.

San Francisco Bay Area

* Built machine learning and data science solutions for user acquisition and marketing team. Collaborated with product managers, data engineers, and machine learning engineers to work on various prototypes* Designed and implemented a cohort-level life time value model, improving the efficiency of marketing budget allocation process and making it more streamlined* Developed a user-level lifetime value model to be consumed by marketing team and customer service team

Mountain View, Ca

Data Engineer @ Intuit Data Engineering and Analytics (IDEA)* Worked on a batch ingestion pipeline that handled data from various sources to be consumed by data scientists* Responsible for end to end maintainability of Ziplock (a tool for testing parity between two databases)* Implemented a metrics and monitoring framework to collect metrics about the data ingestion pipelines

Mountain View, Ca

* Member of data team, working on maintaining, building and improving data pipeline* Developed core data acquisition pipeline and created entities which were fed to the knowledge graph* Built ETL pipeline for Wikipedia data dump and that data served different modules such as search and ranking* Created various analytics of crawlers and parsers data to detect pipeline irregularities and gather statistics* Constructed directed crawling approach for various sources and worked on improving crawlers and parser

San Jose, Ca

* Member of the agile development team for security and customer service platforms. Worked on data pipeline to capture the tickets generated by user’s network devices and creating data analytics of the generated tickets

Chapel Hill, Nc

* Responsible for entire SDLC and full-stack development of the rate management product features* Created data analytics reports to help clients maintain their contracts and improved the efficiency of business by 25%* Improved performance of quote create module by adding critical features, improved SQL’s and data cleaning

Mountain View, Ca

* Worked on HttpJson automation framework (built on Apache Jelly, Java, XML) that automates the verification of product features* Enhanced the existing framework by automating approximately 70% of tests covering all the major modules* Made complete refactoring of the existing framework by decoupling the Jelly context from test case logic to incorporate more stability, flexibility and usability* Introduced data driven approach for similar tests by consolidating data creation and result comparison process* Responsible for bug fixes of both older and enhanced version of framework and for the product as well* Wrote Unit and Integration test cases in JUnit for different modules and also involved in regression testing

Artificial Intelligence

* Machine Learning by Prof. Andrew Ng * Natural Language Processing with Deep Learning by Prof. Chris Manning

Data Science Fellow

Capstone Project: Fake News Detection using Machine Learning * Built an end to end NLP pipeline for news data collection, aggregation.

Master'S, Computer Science, 3.85/4.0

Academic Projects: * Mutual Exclusion Service (Java, Unix) Implemented a mutual exclusion service using Maekawa’s quorum-based algorithm.

Bachelors, Information Technology