Probabilistic Programming Bayesian Jobs in New Mexico

Job Summary:
Los Alamos National Laboratory is a multidisciplinary research institution engaged in strategic science on behalf of national security. They are seeking a highly motivated post-doctoral candidate in the areas of machine learning and AI for materials science, focusing on establishing structure-property relationships from materials datasets. The role involves integrating with project teams and conducting original research with the aim of publishing findings in peer-reviewed journals.
Responsibilities:
• Demonstrated expertise in one or more of the following: Machine learning for materials data, including regression and classification on materials and microstructure datasets.
• Materials modeling experience relevant to microstructure and mechanics (e.g., MD/DFT, phase-field, crystal plasticity, microstructure-property relationships).
• Uncertainty quantification (UQ) and model reliability, including approaches such as calibrated probabilistic prediction, Bayesian/ensemble methods.
• Development and use of atomic-scale descriptors for learning from atomistic datasets (SFD, ACE, MTP, SNAP), including feature construction, and integration into ML workflows.
• Strong programming skills in Python (e.g., NumPy/SciPy, pandas,) and ML frameworks such as scikit-learn, PyTorch, JAX, and TensorFlow.
• Demonstrated experience in conducting original scientific research through peer reviewed publication record.
• Excellent communication skills (both oral and written).
Qualifications:
Required:
• Demonstrated expertise in one or more of the following: Machine learning for materials data, including regression and classification on materials and microstructure datasets.
• Materials modeling experience relevant to microstructure and mechanics (e.g., MD/DFT, phase-field, crystal plasticity, microstructure-property relationships).
• Uncertainty quantification (UQ) and model reliability, including approaches such as calibrated probabilistic prediction, Bayesian/ensemble methods.
• Development and use of atomic-scale descriptors for learning from atomistic datasets (SFD, ACE, MTP, SNAP), including feature construction, and integration into ML workflows.
• Strong programming skills in Python (e.g., NumPy/SciPy, pandas,) and ML frameworks such as scikit-learn, PyTorch, JAX, and TensorFlow.
• Demonstrated experience in conducting original scientific research through peer reviewed publication record.
• Excellent communication skills (both oral and written).
• A STEM PhD in areas such as Materials Science, Computational Physics, Engineering, or related fields, completed within the last five years or soon to be completed.
Preferred:
• Solid Background in materials science and engineering.
• Experience training ML/AI models at scale on GPU-accelerated HPC systems, including managing large datasets/workloads and performance-aware workflows.
• Ability to adapt to new requirements for projects and be flexible enough to learn new areas of research as needed.
• Ability to work effectively as a part of a team in a multi-disciplinary environment and interact with people with a variety of expertise.
Company:
Los Alamos National Laboratory, a multidisciplinary research institution engaged in strategic science on behalf of national security, is Founded in 1943, the company is headquartered in Los Alamos, USA, with a team of 10001+ employees. The company is currently Late Stage.