Jordan Y. Aljbour
Climate & Energy Researcher · Computational Scientist · Python Developer
A computational and data scientist working at the intersection of climate science, energy systems, and high-performance computing — turning complex physical datasets into reproducible, decision-grade tools.
At a glance
40%+
Runtime & memory cut on distributed HPC pipelines running 10k+ Monte Carlo samples per scenario
69
Energy technologies scored in EPRI’s Technology Radar methodology
10+
Peer & industry publications across energy and climate science
6
Professional certifications earned or in progress (AEE, IBM, Google, WRI)
What I do
I build the computational machinery behind environmental and energy decisions, because I believe the people making those decisions deserve the clearest possible picture of what’s at stake. That conviction shapes how I work. I write end-to-end, reproducible scientific software: distributed data pipelines, statistical and risk models, and analysis-ready geospatial tooling, engineered to scale from a laptop to HPC and cloud clusters without ever cutting corners on rigor or reproducibility.
The questions I take on are the ones where the science has real consequences for the planet. How much will a warming climate cost our aging energy infrastructure? What will AI and data centers truly demand from the grid? How are global methane and ethane emissions actually trending, and where can we intervene? I turn messy physical data into honest tools that answer those questions with quantified uncertainty, because good stewardship starts with telling the truth about the numbers.
Most recently, as a Senior Python Developer in parallel computing at ICF, I converted experimental climate workflows into modular, tested, containerized Python packages. I engineered Dask pipelines for out-of-core processing and standardized ARCO-compliant geospatial formats (Zarr, NetCDF) on AWS S3, cutting runtime and memory by 40%+ in the process.