Neelisha Saxena is a Data and Applied Scientist II based in Gurugram with nine years of experience building AI/ML and large-scale analytics solutions across computer vision, NLP, and time-series forecasting. At Microsoft she advances production-ready language and datetime understanding—contributing to the well-known microsoft/Recognizers-Text project by improving datetime resolution, recurrence handling, and task-specific behaviors. Her background spans end-to-end ML systems including real-time pose-estimation pipelines with Kafka, document digitization and table detection for unstructured legal documents, and demand forecasting models, showing a consistent focus on turning research into reliable products. Comfortable across research and engineering, she pairs solid academic CS foundations with practical impact—such as achieving 80% document-level accuracy on in-house extraction—and a knack for improving edge cases in open-source NLP tooling.
9 years of coding experience
5 years of employment as a software developer
High School, Computer Science, High School, Computer Science at Mariampur Senior Sec School
Bachelor’s Degree, Computer Science, Bachelor’s Degree, Computer Science at JSS ACADEMY OF TECHNICAL EDUCATION, NOIDA
Microsoft.Recognizers.Text provides recognition and resolution of numbers, units, date/time, etc. in multiple languages (ZH, EN, FR, ES, PT, DE, IT, TR, HI, NL. Partial support for JA, KO, AR, SV). Packages available at: https://www.nuget.org/profiles/Recognizers.Text, https://www.npmjs.com/~recognizers.text
Role in this project:
Back-end Developer
Contributions:105 reviews, 8 commits, 14 PRs in 6 months
Contributions summary:Neelisha primarily focused on enhancing the datetime recognition capabilities of the `microsoft/recognizers-text` repository. Their contributions include integrating a new "TasksMode" for specific datetime resolutions, customizing resolutions for past datetime references, and supporting the merging of holiday and time references. The user also addressed specific behaviors and suppressed unwanted cases under TasksMode, improving the accuracy and functionality of the library. Furthermore, the user made modifications to enhance the recurrence support in the extractor.
Microsoft.Recognizers.Text provides recognition and resolution of numbers, units, and date/time expressed in multiple languages (ZH, EN, FR, ES, PT, DE, IT, TR, HI, NL. Partial support for JA, KO, AR, SV). Contributions are greatly welcome! Packages are available at https://www.nuget.org/profiles/Recognizers.Text and https://www.npmjs.com/~recognizers.text
Contributions:37 PRs, 181 pushes, 8 branches in 6 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.