About
I'm a machine learning engineer and Earth systems researcher working at the intersection of scientific software, high-performance computing, and geospatial AI. As a Scientist III at the National Center for Atmospheric Research (NCAR) and a PhD researcher at the University of Washington, I build distributed systems that turn satellite and sensor data into environmental predictions — from continental-scale HPC snow simulation to operational machine learning platforms running for the Bureau of Reclamation.
My path here started in geology and environmental engineering before moving into data science and machine learning at scale — a background that shows up in how I approach ML systems: model quality matters, but so does the pipeline, the monitoring, and whether the system still works when an upstream data feed breaks at 2am.
Experience
Scientist III · National Center for Atmospheric Research (NCAR)
Nov 2020 – PresentBoulder, CO
- Architected and implemented Parallel SnowModel for distributed continental-scale snow simulations across HPC systems.
- Designed scalable geospatial data assimilation pipelines fusing multi-source remote sensing observations (MODIS, Sentinel-1, Airborne Snow Observatory) with physically based land surface models.
- Designed, deployed, and maintained an operational machine learning platform supporting reservoir operations for the Bureau of Reclamation, owning automated daily data pipelines and production reliability.
- Designed modular Python software libraries and reproducible workflows for large-scale geospatial machine learning across HPC and operational environments.
- Developed an AI-assisted quality assurance workflow using Ai2's OLMo language model to identify anomalous observations in environmental monitoring time series.
PhD Researcher · University of Washington
Sep 2022 – PresentSeattle, WA
- Collaborated with wildlife ecologists to develop geospatial models relating snow conditions to predator-prey interactions using large environmental datasets.
- Developed a scalable software framework comparing Sentinel-1 SAR observations with physically based snow models and field observations to characterize snowmelt progression.
- Designed multimodal deep learning architectures integrating terrain, airborne lidar, satellite observations, in-situ measurements, and model outputs to optimize environmental monitoring network design.
- Published peer-reviewed research spanning remote sensing, scientific machine learning, distributed environmental modeling, and Earth system prediction.
Data Quality Analyst / Data Manager · B3 Insight
Jun 2019 – Nov 2020Denver, CO
- Automated Python workflows for data validation and quality improvement across large SQL databases.
Staff Engineer · City and County of Denver
Sep 2017 – Jun 2019Denver, CO
- Designed green infrastructure experiments for pollutant mitigation in urban stormwater systems.
Staff Geologist · GEI Consultants, Inc.
Sep 2014 – Apr 2017Woburn, MA
- Conducted environmental field studies and contributed to technical reporting.
Education
PhD, Hydrology & Hydrodynamics
Expected Fall 2026University of Washington
M.S., Data Science
Jun 2025University of California, Berkeley
Coursework: Machine Learning Systems Engineering, Machine Learning at Scale, Generative AI Foundations, Computer Vision, Applied Machine Learning, Fundamentals of Data Engineering
M.S., Hydrology and Environmental Engineering
May 2019Colorado School of Mines
B.A., Geology (Minor: Economics)
May 2013Colgate University
Skills
Programming Languages
Machine Learning
Computing
Geospatial & Remote Sensing
Software Engineering
Outside the Lab
Most of the terrain I study, I also spend time in — skiing, hiking, backpacking, and climbing in the mountains of the Pacific Northwest, and photographing the same alpine landscapes that show up in the datasets I work with.