Nile Wilson is a Senior Data Scientist with 6+ years building production-grade ML/AI solutions at Microsoft, blending biomedical engineering rigor with product-focused delivery. He leads end-to-end initiatives that align technical design to business goals, from problem formulation through deployment, and has stepped into people management as a Senior Data Science Manager. His open-source work includes a TF-IDF recommender for the COVID-19 Open Research Dataset and adding DICOM image redaction to Microsoft Presidio, reflecting a focus on practical, privacy-aware ML for health and enterprise data. Trained as a PhD bioengineer, he brings domain expertise in human health and neural engineering to ML system design, emphasizing societal context and Responsible AI principles in his work. Colleagues rely on him to balance innovation with safety—whether building assistive medical algorithms or business-facing automation—ensuring models are useful, auditable, and ethically considered. Based in New York, he combines academic depth with track record shipping robust, production systems at scale.
7 years of coding experience
12 years of employment as a software developer
Doctor of Philosophy - PhD, Bioengineering, Doctor of Philosophy - PhD, Bioengineering at University of Washington
Bachelor of Science (BS), Biomedical Engineering, Bachelor of Science (BS), Biomedical Engineering at University of Virginia
An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.
Role in this project:
Back-end Developer
Contributions:110 reviews, 100 commits, 49 PRs in 2 months
Contributions summary:Nile's primary contributions involve enhancing the `presidio-image-redactor` module within the `microsoft/presidio` repository. They focused on adding DICOM image redacting capabilities, which included developing a `DicomImageRedactorEngine` class and integrating it into the module. The user refactored the image redactor module to include DICOM image support as an extension and made various improvements to functionality, including allowing the selection of redaction approaches and the ability to return redacted bounding boxes. They also addressed code quality by incorporating linting fixes and addressing typo corrections.
Contributions:34 commits, 2 PRs, 37 comments in 1 year 9 months
Contributions summary:Nile's commits focus on developing a TF-IDF content-based recommendation system for the COVID-19 Open Research Dataset. Their work involves loading and cleaning data from Azure Open Datasets, extracting public domain articles, and creating a `TfidfRecommender` class to build and fit the TF-IDF model. They implemented tokenization using `scibert`, fit the vectorizer, and created functions to extract information about recommendations. Unit tests are also implemented for the TF-IDF utils.
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.