Spencer Clark
Senior Research Scientist at Ai2
New Jersey, United States
Summary
🤩
Rockstar🎓
Top SchoolSpencer Clark is a Senior Research Scientist and software engineer with a decade of experience at the intersection of atmospheric science and scalable scientific computing. He combines deep domain expertise from a Ph.D. in Atmospheric and Oceanic Sciences with hands-on engineering—running multi-node FV3GFS/FV3 simulations on HPC, producing terabyte-scale training datasets, and implementing online coarse-graining for climate models. At Ai2 and Vulcan he merged ML-driven parameterizations with traditional models to improve precipitation and temperature forecasts across climates, and his open-source contributions to xarray improved cftime handling for non-standard calendars and nanosecond-precision datetimes. Based in New Jersey, he mentors and builds reproducible research infrastructure that bridges high-resolution simulation, machine learning, and production-ready Python tooling. Not obvious from the title: he’s run global 3-km simulations whose outputs were coarse-grained online to produce 50+ TB datasets specifically tailored for ML training.
10 years of coding experience
7 years of employment as a software developer
Advanced Studies Diploma, Advanced Studies Diploma at Thomas Jefferson High School for Science and TechnologyBachelor of Science (B.S.) Engineering Physics Honors in Research, Bachelor of Science (B.S.) Engineering Physics Honors in Research at Cornell UniversityDoctor of Philosophy (Ph.D.) Atmospheric and Oceanic Sciences, Doctor of Philosophy (Ph.D.) Atmospheric and Oceanic Sciences at Princeton University
Stackoverflow
1,969reputation
78kreached
53answers
0questions
python
top-5%
Github Skills (12)
data-analysis10
pandas10
xray10
time-series10
python10
numpy10
xa10
haversine6
datetime6
julian-date6
netcdf6
matplotlib6
Programming languages (8)
Github contributions (5)
pydata/xarray
Feb 2017 - Nov 2022
N-D labeled arrays and datasets in Python
Role in this project:
Back-end Developer
Back-end DeveloperContributions:230 reviews, 73 commits, 123 PRs in 5 years 10 months
Contributions summary:Spencer primarily focused on improving the handling of time-related data within the xarray library, as evidenced by the commits related to cftime and pandas. They addressed issues related to the use of cftime.datetime objects, including indexing, arithmetic operations, and the creation of custom time indexes. The user implemented enhancements and bug fixes associated with date and time handling, with a focus on the integration of cftime and improved accuracy when dealing with nanosecond-precision datetimes. Their work improved the library's capabilities for handling time series data with non-standard calendars and dates outside the typical timestamp range.
pythonnetcdfnumpydaskarrays
spencerkclark/dotfiles
Apr 2017 - Jun 2023
Contributions:25 pushes, 3 branches in 6 years 2 months
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.