Drimva

The Allen Institute for AI

Young Investigator, Climate Modeling

$160K

Seattle, WA +1 · Full-time · Posted Sep 25, 2026

Location
Seattle, WA
Seattle, WA, United States
Experience
Substantial relevant ML application-building and deployment experience; no number of years specified.
Education
Ph.D. in computer or computational science, applied mathematics/statistics, atmospheric science, or a related geophysical science.
Visa sponsorship
The employer participates in E-Verify and verifies work authorization after a job offer and completion of Form I-9.

About the job

Lead development and evaluation of an open-source, AI-first hybrid climate model designed to improve climate projections in unseen climates.

What you'll do

  • Design and evaluate model training and testing cases using historical data and customized physics-based climate model outputs.
  • Collaborate on model improvements, including coupling to an ML-based ocean model and improving generalization to unseen climates.
  • Present research at conferences and in publications; contribute to open-source development and mentor interns as appropriate.

What they ask for

  • Substantial experience building and deploying a relevant ML application in practical or academic research.
  • Fluency in Python and collaborative coding practices.
  • Ph.D. in computer or computational science, applied mathematics/statistics, atmospheric science, or a related geophysical science.
  • At least one accepted conference paper or peer-reviewed first-authored publication making extensive use of ML; demonstrated excellent communication skills.

Nice to have

  • Formal training or practical experience with physically-based atmospheric, oceanic, or related model development.
  • Experience writing machine learning code in JAX; formal graduate-level ML coursework.

Pay

$159,650.00 (base salary; currency not stated)

Tools

Python, JAX, NeuralGCM, ACE

AI focus

Develop an AI-powered, physics-informed hybrid climate model that uses historical data to produce more accurate multidecadal forecasts and generalizes to unseen climates.

Model-written summary · the original posting is authoritative

First seen Oct 29, 2026 · Last verified Nov 6, 2026 (UTC)