Caleb Robinson
Principal Research Scientist at Microsoft
Seattle, Washington, United States
Summary
🤩
Rockstar🎓
Top SchoolCaleb Robinson is a Principal Research Scientist at Microsoft with 13 years of experience bridging applied machine learning, geospatial data, and software engineering. He holds a Ph.D. in Computational Science and Engineering from Georgia Tech and progressed through research roles at Microsoft and academia to lead impact-driven AI research in Seattle. Caleb contributes to open-source projects such as Microsoft’s TorchGeo—adding a Kenya crop-type dataset and demonstrating deep expertise in geospatial data pipelines, PyTorch data loaders, and reproducible dataset curation. Comfortable moving between prototype research and production-grade code, he combines strong backend development skills with domain knowledge in remote sensing to deliver tools that enable AI for good. Colleagues describe him as a curious problem-solver who turns complex earth-observation data into usable ML assets.
13 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Computational Science and Engineering, Doctor of Philosophy (Ph.D.) Computational Science and Engineering at Georgia Institute of TechnologyBachelor of Science in Computer Science (BSCS) Computer Science, Bachelor of Science in Computer Science (BSCS) Computer Science at University of Mississippi
Github Skills (17)
pytorch10
sens10
preprocessing10
python10
preprocess10
data-set10
geospatial10
spatial-data10
datasets10
data-preprocessing10
data-loading10
geo10
dataprep10
spatial10
machine-learning9
Programming languages (11)
Github contributions (5)
microsoft/torchgeo
Jun 2021 - Jan 2023
TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data
Role in this project:
Back-end Developer & Data Scientist
Back-end Developer & Data ScientistContributions:1 release, 860 reviews, 210 commits in 1 year 7 months
Contributions summary:Caleb's commits primarily focus on the implementation of a new dataset, the CV4A Kenya Crop Type dataset. The user added a new Python module, `cv4a_kenya_crop_type.py`, which defines the dataset class, and made changes to the `__init__.py` file to import it. The code includes the downloading of the dataset via Radiant Earth MLHub, checking the integrity, and defining methods for accessing the data. The contributions demonstrate a strong understanding of data loading and processing techniques, especially in the context of geospatial data and PyTorch.
pytorchsamplersgeospatialdeep-learningearth-observation
calebrob6/migration-lib
Feb 2017 - Mar 2018
Contributions:12 commits, 11 pushes, 1 branch in 1 year 1 month
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.