24 bayesian-inference-tracking Postdoctoral positions at Oak Ridge National Laboratory
Sort by
Refine Your Search
-
(NSSD). In this role, you will conduct fundamental research into the integration of Bayesian methodologies with system dynamics modeling, advancing statistical methods and the open-source scientific
-
modeling, sensitivity and robustness analysis, Bayesian inference, inverse problems, parameter estimation, or model validation. Experience or strong interest in scientific AI/ML, including surrogate or multi
-
machine learning and Bayesian calibration methods to enable multi-scale, multi-physics model development. Complete simulation verification, model validation, uncertainty quantification, and documentation
-
. Preferred Qualifications: Knowledge of Approximate, Local, Rényi, Bayesian differential privacy, and other related definitions. Knowledge of federated learning SOTA algorithms. Knowledge of distributed
-
simulation tasks. Develop and maintain HPC-ready software workflows for distributed training, large-scale inference, scalable data ingestion, and data management on leadership-class computing systems and
-
, multidisciplinary team environment. Preferred Qualifications: Knowledge of uncertainty quantification methods and causal inference for complex environmental systems. Experience with large-scale Earth system
-
AI processes (e.g., model training, inference). Develop agentic AI systems and AI harnessing techniques to enhance model quality, resource optimization, and adaptive execution in diverse workflows
-
supercomputer. The role includes developing and advancing open-source software for large-scale hyperparameter optimization (HPO), neural architecture search (NAS), and Bayesian optimization on distributed HPC
-
that combines mechanistic ecophysiology with AI, such as: Physics-informed machine learning and neutral networks to investigate plant physiological / abiotic relationships Bayesian statistics and neural and
-
expertise in methods such as machine-learning force-fields for spinful materials, or multi-fidelity Bayesian models that can learn machine-learning force-fields along with effective spin Hamiltonians from ab