> Markdown version of [/jobs/ext/4771318-postdoctoral-research-associate-for-data-driven-alloy-design-and-materials-imaging](https://www.wearedevelopers.com/jobs/ext/4771318-postdoctoral-research-associate-for-data-driven-alloy-design-and-materials-imaging). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Postdoctoral Research Associate for Data-Driven Alloy Design and Materials Imaging - **Company:** Los Alamos National Laboratory - **Location:** Los Alamos, NM, United States - **Contract:** Permanent contract - **Skills:** Computer Vision, Computer Programming, Computer Literacy, Image Analysis, Digital Signal 1, Experimental Data, Graphical User Interface, Java GUIs, Python (Programming Language), Machine Learning, OpenCV, Tensorflow, Azure Machine Learning, Supercomputing, Pytorch, Convolutional Neural Networks, Scikit Learn, HuggingFace, Calc, Data Analytics, Streamlit Framework - **Published:** November 18, 2026 - **Apply:** https://www.careerbuilder.com/job-details/postdoctoral-research-associate-for-data-driven-alloy-design-and-materials-imaging-los-alamos-nm--014bfe89-6fa9-41b1-8c58-7631405dd5bf ## About the Role Chemistry, Machine Learning, Physics, Material Science, Radiography, Computer Vision, T-1 / DS1, DFT (Design for Test), Machine Tool, Data Modeling, Demonstrated expertise in machine-learning-driven alloy design and in one or more of the following: 1. Machine-learning-driven materials design, including surrogate modeling of composition-processing-microstructure-property relationships, Bayesian optimization/active learning, or generative models for alloys (e.g., high-entropy, refractory, or structural alloys). 2. Experience in training and fine-tuning machine learning models with PyTorch, TensorFlow, including computer vision models (e.g., U-Net, YOLO, Vision Transformers, and foundation models such as Segment Anything (SAM)) for segmentation/classification of defects. 3. Materials modeling/atomistic simulation experience relevant to alloys (e.g., MD/DFT, microstructure-property relationships, defect physics, or related modeling approaches). 4. Strong programming skills in Python (mainly PyTorch, scikit-learn, OpenCV). * Demonstrated experience in conducting original scientific research through peer reviewed publication record. * Excellent communication skills (both oral and written). * Ability to get Q clearance, which often requires US citizenship. Education/Experience: A STEM PhD in areas such as Materials Science, Metallurgy, Computational Physics, Engineering, or related fields, completed within the last five years or soon to be completed., * Solid Background in materials science and engineering, preferably in metallurgy/physical metallurgy of alloys, with working knowledge of computer vision. * Knowledge of alloy thermodynamics (e.g., phase diagrams, phase stability, Thermo-Calc or similar tools). * Experience in training machine learning and CV models on GPU-accelerated super computers, with large workloads, and familiarity with PyTorch Lightning, Hugging Face, LangChain, matminer, pymatgen etc. * Experience building graphical user interfaces (GUIs) and interactive tools for machine learning and image analysis workflows (e.g., Streamlit). * 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., *Eligibility requirements: To obtain a clearance, an individual must be at least 18 years of age; U.S. citizenship is required except in very limited circumstances. See DOE Order 472.2 for additional information. ## Description Postdoctoral Research Associate for Data-Driven Alloy Design and Materials Imaging, This postdoctoral position is part of a larger effort with two projects. The first project focuses on accelerating the design and discovery of structural alloys using machine learning tools, such as surrogate models, Bayesian optimization/active learning, and generative models, integrated with DFT, MD, thermodynamic modeling, and experimental data for alloy design. The second project focuses on developing and utilizing computer vision models for characterizing materials micrographs/radiographs/CT and classifying defects, interfaces, and joints, to connect derived features to materials structure-property relationships. The successful applicant will be expected to integrate with the project team broadly and coordinate with experimentalists. We provide unique opportunities for cross disciplinary collaborations, scientific workshop organization, and conference attendance. Outstanding applicants may be nominated for prestigious LANL-funded fellowships, enabling the pursuit of independent research. What You Need