At Amazon Advertising, I developed scalable backend services and data pipelines using AWS technologies including ECS, Lambda, DynamoDB, Step Functions, Glue, and Athena. I built robust ad labeling systems that supported pre- and post-bid filtering to improve ad relevancy, while separately enhancing brand safety systems to protect advertisers and ensure compliance. My work enabled efficient large-scale processing and evaluation of ad data, boosting overall ad quality. I also led seamless service transitions and implemented automation to improve operational reliability and customer onboarding.

At UMBC, I built automation scripts to streamline academic workflows by downloading, organizing, and processing emailed submissions into structured spreadsheets for efficient grading. I designed and maintained a WordPress-based website to showcase ongoing research initiatives and lab members, improving visibility and collaboration. In parallel, I conducted research on fake news detection using Transformer-based models as part of the AI-SSGL Lab, contributing to applied NLP research. I also mentored students across courses including Information Retrieval, Computer Security, Discrete Structures, and Numerical Computations, supporting both conceptual understanding and hands-on problem solving.

At NXP, I modernized the test suite using Python and Keras, applying advanced machine learning techniques including NLP and unsupervised learning to reduce runtime by 30% and cut manual intervention by 50%. I built a PyQt-based user interface to automate preprocessing of large datasets, enabling intuitive querying and visualization of data to support business analysis. I also partnered closely with software testing teams to understand their pain points, documented technical gaps, and researched machine learning–driven solutions, including defining data requirements from the existing technology stack to enable effective adoption.