Student Assistant - Workflow Development

Brookhaven National Laboratory • Upton, NY

5d

About The Position

Brookhaven National Laboratory is committed to employee success and we believe that a comprehensive employee benefits program is an important and meaningful part of the compensation employees receive. Review more information at BNL | Benefits Program Organization Overview: The Center for Functional Nanomaterials (CFN) at Brookhaven is a DOE-funded national scientific user facility, offering users a supported research experience with top-caliber scientists and access to state-of- the-art instrumentation. The CFN mission is advancing nanoscience through frontier fundamental research and technique development and is the nexus of a broad collaboration network. Each year, CFN staff members support the research of nearly 600 external facility users. Three strategic nanoscience themes underlie the CFN scientific facilities: The CFN conducts research on nanomaterial synthesis by assembly designing precise architectures with targeted functionality by organizing nanoscale components. The CFN researches and applies platforms for state-of-the-art techniques for Accelerated Nanomaterial Discovery, integrating synthesis, advanced characterization, physical modeling, and computer science to iteratively explore a wide range of material parameters. The CFN develops and utilizes advanced capabilities for studies of Nanomaterials in Operando Conditions for characterizing materials and reactions at the atomic scale in real-world environments. This project will focus on extending a Python-based workflow for compositional tuning and oxygen-vacancy formation in layered Li transition-metal oxides relevant to battery cathodes. The workflow automates building and modifying surface structures, submitting DFT calculations, post-processing electronic structure and vacancy energies, and extracting machine-learning descriptors for modeling oxygen stability in compositionally tuned local coordination environments. In this position, you will help generalize and document this workflow so that it can start from bulk structures (e.g., from the Materials Project), automatically generate surface models and compositional variants, and carry out analysis and machine-learning modeling of the resulting data.

Requirements

• Must be a college or graduate student in chemistry, materials science, physics, computer science, or a related STEM field.
• You have strong programming skills in Python and experience with scientific computing libraries (e.g., NumPy, pandas).
• You are comfortable working in a Linux/Unix environment, including basic shell scripting and running jobs on remote systems or clusters.
• You communicate effectively, both verbally and in writing.
• You are committed to fostering an environment of safe scientific work practices.

Nice To Haves

• You have experience with electronic-structure or atomistic simulation workflows (e.g., VASP, Quantum ESPRESSO) and associated Python tools such as ASE and pymatgen.
• You have prior experience with machine-learning tools in Python (e.g., scikit-learn) and familiarity with regression modeling and feature importance/interpretability methods (e.g., SHAP).
• You have background knowledge in computational chemistry or materials physics, especially in modeling battery cathode materials, oxygen release, or defect/vacancy formation.
• You have experience with good software practices, including version control (Git/GitHub), code documentation, and basic testing.
• You have prior experience working with BNL facilities.
• You can work effectively in a collaborative team to tackle challenging problems, such as understanding complex scientific data.

Responsibilities

• You will extend and maintain a Python-based workflow to generate, modify, and submit DFT calculations for compositionally tuned layered oxide surfaces and vacancy structures.
• You will generalize the workflow to start from bulk structures (e.g., Materials Project entries), automatically construct surface slabs, and create targeted compositional variants and vacancy configurations.
• You will implement and refine post-processing steps to extract electronic-structure descriptors (e.g., vacancy energies, PDOS-derived quantities, band centers, bond metrics) into machine-learning–ready datasets.
• You will incorporate and compare machine-learning models (e.g., random forest and alternative regression methods), including model evaluation and feature-importance analysis (such as SHAP).
• You will assist in data organization, documentation, and preparation of workflow tutorials and example notebooks for other CFN researchers.
• You will support scientific outputs (figures, tables, and analysis) for manuscripts on oxygen-vacancy formation and compositional tuning in layered Li oxides.

What This Job Offers

• Job Type: Full-time
• Career Level: Intern
• Education Level: No Education Listed
• Number of Employees: 1,001-5,000 employees