Keyur Patel
Director Of Machine Learning at ROC
Denver, Colorado, United States
Summary
🤩
Rockstar🎓
Top SchoolKeyur Patel is a Director of Machine Learning with 10 years of software engineering experience, blending hands-on ML research and production engineering from Denver. He earned his CS degrees at Michigan State University with high honors and accelerated completion, and continues graduate study while leading ML efforts at ROC. His background spans biometrics and face liveness detection—contributing substantive evaluation and refactor work to the open-source OpenBR project—alongside full-stack and systems experience in .NET, C#/C++, Hadoop, SQL, and OpenCV. Known for turning research prototypes into deployable solutions, he has a track record of automating tedious processes (e.g., significant threading and automation wins at Boeing) and presenting technical work to industry leaders. Practical, cross-disciplinary, and results-oriented, he bridges academic rigor with production delivery.
10 years of coding experience
2 years of employment as a software developer
Master's degree Computer Science, Master's degree Computer Science at Michigan State University
English, Gujarati, Spanish, Hindi
Github Skills (8)
computer-vision10
machine-learning10
biometrics10
c-language10
cprogramming-language10
evaluation10
metric10
python9
Programming languages (2)
Github contributions (5)
biometrics/openbr
Jul 2016 - Sep 2021
Open Source Biometrics, Face Recognition
Role in this project:
Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:5 reviews, 30 commits, 19 PRs in 5 years 2 months
Contributions summary:Keyur primarily contributed to the OpenBR project by adding and refactoring code related to the evaluation of biometric liveness detection. They implemented an `EvalEER` function and integrated it into the application, along with related function calls and header declarations. The user also refactored the existing `EvalLiveness` function. Furthermore, they fixed a bug in print statements and added a check to ensure the keys exist in the templates' metadata. These changes suggest a focus on enhancing the project's biometric evaluation capabilities.
pythonface-recognitionrecognitioncomputer-visionbiometrics
isaacedem/wifidirect_multihop
Mar 2016 - Apr 2016
Contributions:15 commits, 12 pushes in 24 days
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.