Bed Bath & Beyond | Overstock.com
I work in Product Discovery research that has its applications in Recommendation Systems, Search and Ranking, and content quality in general. Here are few of the projects that I have lead.
- Design, implement, deploy, and maintain core machine learning algorithms for product discovery and personalization.
- Designed and developed a novel Matrix-Factorization-like Product Embeddings that provide Matrix Factorization quality recommendations but with a 1/10th of computational costs.
- Designed and developed an efficient approach to efficiently bind multimodal information into a single embedding space.
- Designed a content-based complementary product recommendation approach that doesn't rely on the Co-purchases data.
- Extracting product attributes from product images.
- Fine-tune and Deploy Large Language Models (LLMs) and other Generative AI methods to perform various tasks.
- Mentored interns through research projects, and supported and assisted in the design and development of an in-house embedding analysis and visualization tool for ML scientists.
University of Alabama in Huntsville
Artificial Intelligence for Criminal Justice Reform, National Institute of Justice, Department of Justice, United States
The project aimed at developing an Artificial Intelligence (AI) based mobile app that would help paroles from correctional facilities, as a part of the initiative to reduce recidivism. Worked on building a job recommender system for paroles.
The project aimed at developing an Artificial Intelligence (AI) based mobile app that would help paroles from correctional facilities, as a part of the initiative to reduce recidivism. Worked on building a job recommender system for paroles.
United States Army Research Lab
Research project under the US-India Defense Technology and Trade Initiative (DTTI)
Helped with designing and developing a Virtual Reality interface with multimodal interaction capabilities including natural hand gesture recognition, speech recognition, and eye gaze for enhanced natural human-computer interaction in Virtual Reality. Also, conducted multiple user studies as a part of user-interface/user-experience (UI/UX) research and published technical papers at reputed conferences and journals.
Some of the work products can be seen below.
Helped with designing and developing a Virtual Reality interface with multimodal interaction capabilities including natural hand gesture recognition, speech recognition, and eye gaze for enhanced natural human-computer interaction in Virtual Reality. Also, conducted multiple user studies as a part of user-interface/user-experience (UI/UX) research and published technical papers at reputed conferences and journals.
Some of the work products can be seen below.
University of Central Florida, Orlando
United States Air Force Research Labs, University of Florida Research and Engineering Education Facility, Eglin, Florida.
Part of the summer program working on research projects with applications to US Air Force.
Built a novel end-to-end Machine Learning model that outperformed the state-of-the-art ML-based approach for Radio Signal Direction Finding in GPS-denied environments.
Part of the summer program working on research projects with applications to US Air Force.
Built a novel end-to-end Machine Learning model that outperformed the state-of-the-art ML-based approach for Radio Signal Direction Finding in GPS-denied environments.