Experience

Research and industry positions.

2025 – Present

Postdoctoral Researcher

Research Corporation of Hawaii — Honolulu, HI

  • NASA SWOT foundation model: Leading end-to-end design and training of a domain-informed self-supervised foundation model on terabyte-scale satellite data using multi-GPU distributed training on HPC infrastructure.
  • Production satellite ML pipelines: Building image retrieval and semi-supervised learning systems on the WV-Net foundation model, processing millions of ESA Sentinel-1 SAR images for atmospheric science and oceanography applications.
  • Clinical foundation model: Refining a dual-energy X-ray foundation model with fairness-aware evaluation pipelines, ensuring stable subgroup performance across mortality risk, cardiovascular health, fracture risk, and metabolic disease prediction.
2019 – 2025

Graduate Research Assistant

University of Hawaii at Manoa — Honolulu, HI

  • WV-Net SAR foundation model: Built end-to-end data and training pipeline for 12M+ satellite images spanning 9 years of global coverage; achieved 90%+ mAP on rare-pattern retrieval and up to 40% improvement on downstream classification and regression tasks. Published in AMS AI for Earth Systems (2025).
  • DXA healthcare foundation model: Engineered a domain-informed self-supervised embedding model consolidating four NIH longitudinal cohorts; outperformed the WHO clinical hip-fracture risk tool by 10% and enabled mortality prediction. Published in Communications Medicine (2022).
  • Solar atmosphere inversion model: Developed ML model for inverse solar physics trained on terabyte-scale simulation data; deployed into the Daniel K. Inouye Solar Telescope production workflow with sim-to-real monitoring. Published in The Astrophysical Journal (2024).
  • Diffusion-based weather forecasting: Built score-based diffusion downscaling pipeline improving speed, accuracy, and resolution of probabilistic solar and climate forecasts.
  • Additional ML systems: Physics-informed Belle-II particle identification (97% accuracy); tree-structured GNN for microbiome analysis (+30% over baselines); custom pose-estimation pipeline for evolutionary biology lab cutting video analysis time by 95%, from hours to seconds.
2018

Graduate Teaching Assistant

University of Hawaii at Manoa — Honolulu, HI

  • Mentored 60+ students in weekly CS lab sections, reinforcing core computer science concepts through hands-on instruction.
  • Designed individualized tutoring and workshop sessions, driving a 30% increase in student participation over the semester.
  • Partnered with faculty on curriculum development, course structure, and assignment design.
2018

Software Engineering Intern

Mind-Alliance Systems — Washington, D.C.

  • Built a custom NLP named-entity-recognition web scraper, doubling data acquisition throughput via automated collection.
  • Curated a schema.org-derived training dataset, raising NER model accuracy from 50% to ~90% on internal benchmarks.
  • Researched and proposed a graph-database storage stack, reducing data retrieval time by 20% and enabling new structured-knowledge workflows.
2017

Data Science Intern

SAP Labs — Palo Alto, CA

  • Shipped a production chatbot for the conversational AI platform team, reducing average customer response time by 80%.
  • Led adaptation of the chatbot training pipeline for the German market, broadening enterprise linguistic coverage.
  • Engineered a German word embedding model on internal corpora, improving German chatbot performance by 60%+.