Deep Learning Earth System Modeling Evaluation - Postdoctoral Researcher

Overview

Join LLNL as a Postdoctoral Researcher in Deep Learning for Earth System Modeling. Conduct cutting edge research at the intersection of deep learning, atmospheric science, and statistical methods to advance the evaluation and testing of AI-based Earth System models. You will operationalize AI-based weather and climate models and rigorously evaluate their performance against observations and traditional models, collaborating with a multidisciplinary team of experts in machine learning, atmospheric science, Earth System modelling, and model performance assessment.

This position is in the Climate Sensitivity and Impacts Group within the Atmospheric, Earth, and Energy Division. This is a two-year Postdoctoral appointment with the possibility of extension to a maximum of three years.

• Conduct research on the ability of Deep Learning Earth System Models (DL-ESMs) to accelerate Earth System science.
• Apply a set of standard metrics based on DL-ESM outputs, and design, develop and carry out innovative advanced experiments (e.g., storyline analyses, or implementing nudging methods) to evaluate the trustworthiness of DL-ESMs against conventional ESMs and observational datasets.
• Engage and actively contribute to the international initiative AI-MIP, to define a standard set of experiments for evaluating and benchmarking state-of-the-art DL-ESMs.
• Pursue independent research and collaborate with colleagues in a multidisciplinary team environment to advance research goals.
• Prepare comprehensive documentation of findings to guide future users.
• Publish research results in peer-reviewed journals and present results at external conferences and seminars.
• Travel as required to coordinate research with collaborators or participate in relevant hackathons.
• Perform other duties as assigned.

• PhD in Atmospheric Science, Data Science, or related field.
• Experience conducting research in atmospheric science or closely related fields.
• Ability to manipulate and analyze large, complex ESM output datasets, such as those from the Coupled Model Intercomparison Project.
• Proficient programming skills using Python and experience with deep learning frameworks (e.g., PyTorch, Tensor Flow).
• Experience using high-performance computing environments.
• Proficient verbal and written communication skills as evidenced by peer-reviewed publications and presentations.
• Ability to work independently as well as effectively in a collaborative, multidisciplinary team environment.
• Ability to travel as required.

• Experience developing and applying advanced statistical algorithms or machine learning models for applications such as weather forecasting, S2S prediction, storyline analysis, nudging, green function, or dynamical adjustment.
• Familiarity with analysis of weather extremes, variability across time scales, or impacts of extreme events on infrastructure, natural, or human systems.
• Experience with one AI-based weather prediction model (e.g., Neural
  
  GCM, ACE2, Gen Cast, Weather Next
  2).

$123,048 Annually

All your information will be kept confidential according to EEO guidelines.

This is a Postdoctoral appointment with the possibility of extension to a maximum of three years, open to those who have been awarded a PhD at time of hire date.

• Included in 2026 Best Places to Work by Glassdoor!
• Flexible Benefits Package
• 401(k)
• Relocation Assistance
• Education Reimbursement Program
• Flexible schedules (depending on project needs)
• Our values – visit our inclusion page

None required. If your assignment is longer than 179 days cumulatively within a calendar year, you must go through the Personal Identity Verification process. This process includes completing an online background investigation form and receiving approval of the background check. This process does not apply to foreign nationals.

The 2025 NDAA, Section 3112, restricts access for certain non-U.S. citizens without dual citizenship or legal permanent residence. Candidates must be eligible to access the Laboratory in…