Arman Pouyaei, PhD / Data engineering + predictive modeling

I turn weather at scale into decisions.

Senior data engineer and data scientist building production AI, geospatial, and climate-risk systems — from GPU-accelerated forecasting to petabyte-scale delivery.

Start a conversation Download résumé

MSCIPrinceton, NJPython · AWS · GPU

hazard.pipeline / global

domain

climate risk

scale

petabyte

state

● production

Hard science, engineered into production.

I work where research-grade modeling meets operational software: translating open-ended climate questions into auditable systems, clear uncertainty, and products teams can use.

01.1 / CURRENT

Severe-storm intelligence at global scale

Lead MSCI’s blizzard, dust-storm, and sandstorm modeling program end to end — architecture, AI weather emulation, GPU ensembles, validation, and production delivery.

PyTorchJAXCUDAEVT

01.2 / PLATFORM

Petabyte-scale climate data pipelines

Architected containerized ETL on AWS Batch, serving Zarr, Parquet, and NetCDF data to downstream analytics and client-facing products.

AWS BatchS3DockerDask

01.3 / OPEN SCIENCE

Source attribution people can inspect

Built and open-sourced C-TRAIL, a Lagrangian trajectory framework adopted by external research groups to trace downstream outcomes to upstream sources.

GeospatialFortranAtmospheric science

From atmospheric research to enterprise climate risk.

My career connects physical understanding, statistical rigor, and engineering discipline — with increasing ownership of teams, platforms, and product outcomes.

2026 — NOW

Senior Data Engineer (Data Science)

MSCI · New York

Lead global severe-storm hazard modeling; build production ML, ensemble forecasting, extreme-value analysis, and AI-assisted diagnostic workflows across hundreds of millions of records.

2025 — 2026

Data Engineer / Research Scientist

First Street · New York

Designed global ML workflows, automated QA and anomaly detection, and petabyte-scale AWS pipelines for climate-risk analytics before First Street’s acquisition by MSCI.

2023 — 2025

Postdoctoral Research Associate

NOAA GFDL / Princeton University

Led a modeling workstream across four research groups and 8+ scientists; benchmarked predictive components, documented uncertainty, mentored researchers, and published high-dimensional climate analysis.

2018 — 2023

Researcher & Postdoctoral Fellow

University of Houston

Developed Bayesian data assimilation, particle transport, data-fusion, and deep-learning methods; earned a PhD in Atmospheric Science and open-sourced C-TRAIL.

A deep technical range, centered on delivery.

I move comfortably from model formulation to distributed compute, from validation design to executive communication — choosing the level of abstraction the problem needs.

Python

NumPy · pandas · Xarray · GeoPandas

ML / AI

PyTorch · JAX · scikit-learn · TensorFlow

Cloud + HPC

AWS · Docker · SLURM · MPI · CUDA

Data at scale

Dask · Zarr · Parquet · NetCDF

Forecasting

ensembles · time series · uncertainty

Statistics

Bayesian inference · EVT · optimization

Geospatial

transport · exposure · data fusion

Communication

visualization · prototypes · briefings

Credibility built in both code and research.

30+ peer-reviewed publications

Seven first-author papers across climate dynamics, atmospheric chemistry, data assimilation, and modeling systems.

Invited technical speaker

NASA GISS Seminar Series, NOAA GFDL Seminar Series, AGU, AMS, and CMAS.

Cross-functional technical leadership

Coordinates engineers, analysts, scientists, product partners, and client-facing teams around measurable requirements and delivery milestones.

Research community service

Lead convener for an AGU 2026 session and peer reviewer for nine scientific journals.