Reduced Order Modeling - Postdoctoral Researcher

Job Description

The Center for Applied Scientific Computing (CASC) within the Computing Directorate, is seeking a Postdoctoral Researcher with a strong background in computational science, scientific machine learning, reduced-order modeling, or data-driven modeling of physical systems. You will conduct research on the development of fast, trustworthy, and data-efficient surrogate models that integrate physics-based simulations with experimental data and enable artificial intelligence (AI)-agent-assisted scientific workflows.

This position will contribute to multidisciplinary research connecting physical experiments, high-fidelity computational models, surrogate and reduced-order models, and AI agents within automated Design-Build-Test-Compute workflows. Research opportunities include developing methods to reconcile discrepancies between computational models and physical experiments, constructing surrogate models from sparse experimental data, identifying low-dimensional representations of high-dimensional parameter spaces, developing uncertainty-aware and adaptive models, and integrating computational models with AI agents for scientific decision support. Applications will include electrochemical systems and advanced manufacturing, with opportunities to develop broadly applicable methods and software for computational science.

You will

• Conduct research and development in one or more of the following areas: scientific machine learning, reduced-order modeling, surrogate modeling, system identification, equation discovery, uncertainty quantification, active learning, optimization, computational mechanics, and data-driven modeling of physical systems.
• Develop data-efficient computational methods for constructing predictive models from combinations of high-fidelity simulation data and sparse, noisy, or time-dependent experimental observations.
• Develop approaches for reconciling computational models with physical experiments, including parameter calibration, model-discrepancy correction, equation discovery, and hybrid physics/data-driven modeling.
• Develop methods for identifying low-dimensional parameter spaces, latent representations, or active subspaces that enable efficient surrogate construction and experimental exploration.
• Develop uncertainty-aware surrogate models and methods for assessing model validity, detecting out-of-distribution operating conditions, and determining when model predictions can be reliably used for scientific decision support.
• Investigate active-learning and adaptive experimental-design strategies in which computational models and AI agents identify informative operating conditions or experiments for improving surrogate models.
• Develop and integrate surrogate and reduced-order models with AI-agent-compatible software interfaces to enable automated model execution, model updating, optimization, and decision support.
• Apply developed methods to multidisciplinary applications involving physical experiments and computational simulations, including electrochemical systems and advanced manufacturing.
• Design and perform numerical experiments to evaluate model accuracy, computational performance, data efficiency, uncertainty, robustness, and generalization.
• Contribute to the development and utilization of LLNL computational tools for reduced-order modeling and scientific machine learning.
• Contribute to and actively participate in the conception, design, and execution of research addressing defined scientific and engineering problems.
• Pursue independent but complementary research interests and interact with a broad spectrum of scientists and engineers internally and externally to the Laboratory.
• Collaborate with experimentalists, computational scientists, applied mathematicians, software developers, and AI researchers in a multidisciplinary team environment.
• Publish research results in peer-reviewed scientific or technical journals and present results at external conferences, seminars, and technical meetings.
• Perform other duties as assigned.

Qualifications

• PhD in computational science, applied mathematics, computational engineering, mechanical engineering, chemical engineering, computer science, or a related field.
• Experience in one or more of the following areas: scientific machine learning, reduced-order modeling, surrogate modeling, system identification, uncertainty quantification, optimization, numerical methods, or data-driven modeling of physical systems.
• Experience developing or applying computational models to physical or engineering systems.
• Proficiency in Python, C++, C, FORTRAN, or similar scientific computing languages.
• Demonstrated ability to develop and evaluate computational methods using simulation and/or experimental data.
• Demonstrated ability to conduct independent research , as evidenced by publications in peer-reviewed scientific or technical literature.
• Proficient verbal and written communication skills necessary to collaborate effectively in a multidisciplinary team environment and present and explain technical information.
• Demonstrated initiative, creativity, and interpersonal skills as well as the ability to work effectively with researchers from computational, experimental, and software-development backgrounds.

Qualifications We Desire

• Experience with reduced-order modeling, surrogate modeling, or scientific machine learning for physical or engineering systems.
• Experience with system identification, equation discovery, or hybrid physics/data-driven modeling for improving or augmenting physics-based computational models.
• Experience with uncertainty quantification, active learning, sensitivity analysis, or adaptive experimental design, particularly for data-scarce physical systems.
• Experience integrating simulation and experimental data for model calibration, validation, prediction, or decision support.
• Experience with high-performance computing and/or modern machine-learning frameworks, such as PyTorch or JAX.
• Familiarity with AI agents, tool-enabled AI workflows, Model Context Protocol interfaces, or automated scientific workflows.

Salary Range

$143,328 Annually

Additional Information

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

Position Information

This is a Postdoctoral appointment with the possibility of extension to a maximum of three years. The postdoctoral appointment is a temporary, mentored training position intended for individuals in the early stages of their postdoctoral research careers. Consistent with the structure of the program, applicants must have received their Ph.D. (or equivalent doctorate) within five years of the anticipated start date.

Why Lawrence Livermore National Laboratory?

• 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 https://www.llnl.gov/inclusion/our-values

Security Clearance

None required. However, 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.

National Defense Authorization Act (NDAA)

The 2025 National Defense Authorization Act (NDAA), Section 3112, generally prohibits citizens of China, Russia, Iran and North Korea without dual US citizenship or legal permanent residence from accessing specific non-public areas of national security or nuclear weapons facilities. The restrictions of NDAA Section 3112 apply to this position. To be qualified for this position, Candidates must be eligible to access the Laboratory in compliance with Section 3112.

Pre-Employment Drug Test

…