Data-driven and Machine Learning Postdoctoral Research Associate

What You Will Do

The Computational and Physics Methods Group (CAI-2) in the Computing and Artificial Intelligence Division at Los Alamos National Laboratory is seeking a skilled and driven researcher for a postdoctoral position at the intersection of applied mathematics, data-driven modeling of dynamical systems, and machine learning. The successful candidate will join a multidisciplinary team of mathematicians, physicists, and machine learning researchers advancing AI-enabled modeling of complex dynamical systems.

Leveraging transfer operator theory (e.g., Koopman and Perron-Frobenius methods), the postdoc will develop novel learning architectures that both respect physical constraints and help discover underlying structure from data. Core activities will span method development, theoretical analysis, and empirical validation at scale on benchmark and mission-relevant datasets. The position offers exposure to multiple application domains (e.g., wildfire, ocean, and space weather), as well as opportunities for cross-disciplinary collaboration, scientific workshop organization, and conference participation.

Minimum Job Requirements:

• Experience in data-driven and/or ML methods for dynamical systems, as evidenced through a strong scientific record of peer-reviewed publications and presentations.
• Fundamental understanding of the Koopman and/or Perron-Frobenius Operators.
• Excellent scientific programming skills with hands-on experience using modern ML libraries and tools (e.g., PyTorch and/or JAX) and high-level languages such as Python (including Num Py/Sci Py).
• Strong mathematical training in at least one relevant field (e.g., functional analysis/operator theory, probability/stochastic processes, numerical analysis/scientific computing, and/or optimization/ML theory).
• Ability to work both independently and collaboratively in an interdisciplinary environment.
• Ability to communicate technical results clearly in writing and presentations.
• Demonstrated creativity and interest in developing new research directions and original methodologies.

Education/Experience: PhD in Applied Mathematics, Computational or Statistical Physics, Applied Statistics, Computer Science, or a related field completed within the last 5 years or to be completed soon.

Desired Qualifications:

• Prior research experience directly involving the Koopman and/or Perron-Frobenius operators.
• Prior research experience developing and/or implementing neural operators.
• Strong background in functional analysis/operator theory, including spectral theory, reproducing kernel Hilbert space methods, and the approximation of infinite-dimensional systems by finite-dimensional models.
• Experience with probabilistic modeling and uncertainty quantification (e.g., Bayesian deep learning, generative models, variational inference, ensembles, probabilistic scoring rules).
• Experience developing novel neural network architectures (e.g., customized loss functions, complex network topologies, constrained or structure-preserving architectures).
• Experience working with large numerical simulations or high-dimensional datasets and familiarity with high-performance computing environments (e.g., clusters, GPUs, job schedulers).

Work Location: The work location for this position is onsite and located in Los Alamos, NM. All work locations are at the discretion of management.

Due to federal restrictions contained in the National Defense Authorization Act, citizens of certain countries are prohibited from accessing facilities that support the mission, functions, and operations of national security laboratories and nuclear weapons production facilities, which includes Los Alamos National Laboratory.

For full consideration please include:

• A comprehensive CV with publication list
• A cover letter describing your qualifications and how you meet the job requirements
• Contact information for at least three professional references.

For questions about this position contact:
Derek DeSantis (ddesantis) or Yen Ting Lin (yentingl).

For more information, visit LANL career page: LANL career page URL unavailable in this sanitized content.

Outstanding candidates may be…