Justin Polchlopek
Data Engineer
Philadelphia, Pennsylvania, United States
Summary
🤩
Rockstar🎓
Top SchoolJustin Polchlopek is a Data Engineer with 10 years of production software experience who blends deep academic training in economics (PhD) with practical expertise in GIS, remote sensing, and big-data systems like Spark. He has a strong AWS and Kubernetes background and a track record of contributing to notable open-source geospatial projects—helping extend raster-vision for deep learning on satellite imagery and adding MGRS support to GeoTrellis. Comfortable across backend systems and statistical ML, Justin gravitates toward work that connects science and economics and prefers mission-driven organizations (bonus for B-corps). His unusual combination of econometric rigor, hands-on geospatial engineering, and experience building a VSI filesystem for GDAL access lets him bridge data science research and scalable production pipelines.
10 years of coding experience
10 years of employment as a software developer
The University of UtahBachelor's of Science, Computer Science and Engineering, Bachelor's of Science, Computer Science and Engineering at University of Connecticut
Github Skills (15)
unit-testing10
geographical-information-system10
gdal10
filesystem10
gis10
geospatial10
python10
scala10
type-checking9
sens9
typehinting9
computer-vision8
deeplearning-ai7
deep-learning7
pytorch6
Programming languages (16)
Github contributions (5)
locationtech/geotrellis
Apr 2016 - Nov 2020
GeoTrellis is a geographic data processing engine for high performance applications.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:2 reviews, 308 commits, 91 PRs in 4 years 7 months
Contributions summary:Justin primarily contributed to adding and implementing support for the Military Grid Reference System (MGRS) within the project. This involved creating a new module for MGRS support in the core project. The user also added a unit test to verify the accuracy of the MGRS conversions, and made minor fixes to constrain the accuracy of the conversions.
geotrellisgeospatialdata-processinggeographic-dataperformance
azavea/raster-vision
Apr 2020 - Jun 2020
An open source library and framework for deep learning on satellite and aerial imagery.
Role in this project:Back-end Developer
Back-end DeveloperContributions:21 commits, 6 PRs, 7 comments in 1 month
Contributions summary:Justin primarily focused on refactoring and improving the codebase related to vector data processing within the `raster-vision` library. Their contributions involved fixing issues related to vector rasterization and refining type definitions for vector source configurations, demonstrating a deep understanding of the project's core data handling mechanisms. Additionally, the user implemented the initial functionality for a VSI (Virtual Storage Interface) filesystem, enabling access to files over various protocols supported by GDAL. Further improvements included fixing flake errors and code optimizations.
pytorchgeospatialsemantic-segmentationdeep-learningsatellite
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.