Stefan Keselj
Quantitative Developer
Chicago, Illinois, United States
Summary
👤
Senior🎓
Top SchoolStefan Keselj is a quantitative developer in Chicago with a decade of experience applying computer vision and video understanding to real-world problems. He has driven perception and semantic segmentation work at Helm.ai, led a team of six on object segmentation, and previously improved Google Search by extracting information from videos. His background includes research at Princeton using neural nets to correct brain-slice image deformations, reflecting strong roots in applied research and sample-efficient model development. Now working under NDA at a proprietary trading firm, he brings ML-driven perception expertise to high-stakes production systems. Stefan’s focus is on helping people understand sensory data—images, video, and audio—by turning noisy signals into actionable information. Colleagues describe him as a pragmatic engineer who blends research rigor with leadership in shipping robust, production-ready models.
10 years of coding experience
7 years of employment as a software developer
Bachelor's Degree Computer Science, Bachelor's Degree Computer Science at Princeton University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (5)
python-requests2
pytorch1
barrage1
python1
data-provider1
Programming languages (2)
Github contributions (5)
skeselj/safe-city
Mar 2016 - Dec 2017
Contributions:4 PRs, 105 pushes, 2 branches in 1 year 9 months
skeselj/capsule-network-experiments
Jan 2018 - Jan 2018
Pushing the limits of capsule networks.
Contributions:14 commits, 27 pushes, 1 branch in 6 days
limitspushingcapsule-networkscapsule
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.