Nikola Trifunović
Software Engineer at Perplexity
Belgrade, Central Serbia
Summary
🤩
Rockstar🎓
Top SchoolNikola Trifunović is a software engineer based in Belgrade with 15 years of experience building machine learning solutions that improve geospatial data. He led the creation of the first worldwide dataset of building footprints from satellite imagery, demonstrating a rare mix of research-led engineering and production-grade delivery. Passionate about geospatial data modeling, encoding, and retrieval, he focuses on grounding answers in rich spatial context to improve downstream decision-making. Nikola blends individual contributor depth with team development skills, mentoring engineers and establishing practices that scale. Now at Perplexity, he continues to push applied ML for situational awareness and information grounding. A detail that often goes unnoticed: his background in electrical engineering informs a systems-first approach to data pipelines and model integration.
7 years of coding experience
High school degree, High school degree at Gimnazija TrstenikM.Sc.E.E., M.Sc.E.E. at University of Belgrade
German, English, Serbian
Github Skills (22)
mediawiki-extension10
gdal10
geospatial10
gis10
efficientnet8
keras-models7
mobilenet7
resnet6
densenet6
segmentation6
keras-tensorflow6
python-bindings5
image-segmentation5
keras5
openstreetmap4
Programming languages (1)
Github contributions (5)
microsoft/CanadianBuildingFootprints
Feb 2019 - Jun 2019
Computer generated building footprints for Canada
Contributions:7 commits in 3 months
footprintsbuilding-footprints
microsoft/USBuildingFootprints
Jun 2018 - May 2022
Computer generated building footprints for the United States
Contributions:10 commits, 6 PRs, 10 pushes in 3 years 11 months
geospatialmediawiki-extensionbuilding-footprintsgdalfootprints
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.