Roy Shilkrot
Co-Founder at Roy Shilkrot PhD
Greater Boston United States
Summary
🤩
Rockstar🎓
Top SchoolRoy Shilkrot is a technologist and entrepreneur with 15+ years building AI, computer vision, and ML products from research prototypes to production at scale. As Co-Founder of ContentsPal and a former Head of Labs at Tulip, he blends hands-on engineering (C++, Python, ONNX, real-time video) with productization and MLOps to reduce operational risk in industries like insurance and manufacturing. He teaches generative AI and vision at MIT Media Lab and Tufts, mentors grad students, and has a track record of published research, patents, and large academic grants. A prolific open-source maintainer, Roy is the primary developer of practical tooling such as an OBS background-removal plugin and contributions to gesture-recognition libraries that have reached wide adoption. He combines academic rigor from an MIT PhD with startup execution, and outside of work frames himself as a teacher, content creator, and family-oriented maker. Unexpectedly, his OSS projects have been used by millions while he simultaneously ships enterprise ML systems that process millions of transactions.
14 years of coding experience
15 years of employment as a software developer
BSC Computer Science, BSC Computer Science at The Academic College of Tel-Aviv, YaffoPhD Human Computer Interaction Media Arts and Sciences, PhD Human Computer Interaction Media Arts and Sciences at Massachusetts Institute of TechnologyMSc Computer Science, MSc Computer Science at Tel Aviv UniversityIndependent studies Computer Vision, Independent studies Computer Vision at Weizmann Institute of ScienceHigh school diploma Computer Chemistry, High school diploma Computer Chemistry at Tzafit
Hebrew, English, Spanish, Russian
Stackoverflow
3,298reputation
1.1mreached
63answers
2questions
tensorflow
top-5%
twitter
top-5%
python
top-5%
javascript
top-5%
rename
top-5%
Github Skills (30)
opencv10
c-language10
python10
feature-extraction10
video-processing10
machine-learning10
onnx10
plugin10
numpy10
regression10
image-segmentation10
gesture-recognition10
segmentation10
onnxruntime10
computer-vision10
Programming languages (14)
Github contributions (5)
locaal-ai/obs-backgroundremoval
Apr 2021 - May 2022
An OBS plugin for removing background in portrait images (video), making it easy to replace the background when recording or streaming.
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:8 releases, 176 reviews, 76 commits in 1 year
Contributions summary:Roy appears to be the primary developer, responsible for the initial setup and ongoing development of the OBS plugin for background removal. Their work includes creating the core background removal filter functionality within the OBS plugin framework, integrating ONNX runtime for inference, and implementing features such as contour processing and mask smoothing. Further contributions extended to supporting multiple color space conversions, enhancing the plugin's video format compatibility and usability.
portraitmac-osxobsscreen-recordinglibobs
nickgillian/grt
Jul 2018 - Jul 2018
gesture recognition toolkit
Role in this project:ML Engineer
ML EngineerContributions:15 commits, 1 PR, 1 comment in 16 days
Contributions summary:Roy primarily contributed to the development and enhancement of the gesture recognition toolkit, `grt`, by adding and improving classification algorithms and examples. Their work involved the implementation of various machine learning models such as SVM, Softmax, and RandomForests within the project's framework. They refactored existing code and added functionality by integrating pre-processing and post-processing modules and ensuring the compatibility of matrix and vector data structures with NumPy arrays.
recognitiongesturegesture-recognition
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.