Postdoc: AI for Earth System Forecasting & Modeling

Argonne National Laboratory; Lemont (IL); On-site; USD 73,000 - 121,000; Full time

Benefits offered by this job

Comprehensive benefits

Equal opportunity employer

Job summary

Argonne National Laboratory in Illinois invites applications for a postdoctoral appointee in the Decision and Infrastructure Science Division to advance AI foundation models for weather and hydrology and deploy them within infrastructure and resilience workflows.

The successful candidate will collaborate across divisions, develop and benchmark diffusion-based and transformer models, and contribute to reports and publications.

Qualifications

• PhD completed or near completion in geophysical sciences, computer science, or machine learning.
• Experience developing and verifying deep learning models for large dynamical systems.
• Knowledge of data and model parallelism for distributed training on GPUs.
• Familiarity with diffusion-based or generative AI methods and multimodal data training.
• Background in atmospheric science or weather modeling is valued.
• Strong scientific writing and ability to communicate with colleagues.

Responsibilities

• Develop, evaluate, and apply ML/compute approaches for weather and earth system science.
• Benchmark AI foundation models and deploy them for S2S forecasting workflows.
• Collaborate across DIS, Environmental Sciences, and leadership computing facilities.
• Prepare reports, publications, and documentation of results.

Skills

Deep learning

PyTorch

JAX

Large-scale training

Transformers

GNN

Diffusion models

HPC systems

Atmospheric dynamics

Data analysis

Data assimilation

Scientific writing

Effective communication

Problem solving

Team collaboration

Education

PhD in geophysical sciences, CS, or ML

Tools

PyTorch

JAX

HPC environments

Job description

Argonne National Laboratory in Illinois invites applications for a postdoctoral appointee in the Decision and Infrastructure Science Division to advance AI foundation models for weather and hydrology and deploy them within infrastructure and resilience workflows.

The successful candidate will collaborate across divisions, develop and benchmark diffusion-based and transformer models, and contribute to reports and publications.