L

Lawrence Livermore National Laboratory (LLNL)

National security research laboratory

Atomistic and Data-Driven Modeling of Materials for Energy Applications Intern

Applied Machine LearningConfirmed live in the last 24 hours
InternshipLivermore, CA, USA

About the Job

Requirements

  • Must be eligible to access the Laboratory in compliance with Section 3112 of the National Defense Authorization Act.
  • Must have completed, or anticipate completing by the hire date, a Ph.D. in Materials Science, Chemistry, Physics, Mechanical Engineering, or a related field.
  • Experience applying density functional theory and/or advanced electronic structure theory to simulate complex materials, including oxides and multi-element systems.
  • Experience performing large-scale molecular dynamics simulations in high-performance computing environments.
  • Additional experience in at least one of these methods: machine-learning-based approaches, cluster expansion, advanced statistical analysis, kinetic Monte Carlo simulations, phase-field modeling, reduced-order modeling, descriptor development, or surrogate-model development relevant to energy applications.
  • Ability to perform technical assignments with increasing independence, analyze results, and contribute solutions to defined research problems.
  • Ability to contribute to research directions under mentorship and communicate results through peer-reviewed publications and technical presentations.
  • Proficient verbal and written communication skills to collaborate in a team, prepare written reports, and present and explain technical information.
  • Interpersonal skills to interact with scientists, engineers, and technical and administrative staff in a collaborative, multidisciplinary team environment.

Responsibilities

  • Perform electronic structure theory-based simulations of complex materials, such as oxides and multi-element systems.
  • Perform thermodynamic and kinetic analyses of chemical reactions and phase transitions at surfaces and interfaces.
  • Perform non-equilibrium molecular dynamics simulations and first-principles calculations to study materials response under externally applied stimuli.
  • Derive structure-composition-property relationships using statistical, analytical, and machine-learning-based methodologies.
  • Develop machine-learning interatomic potentials and surrogate models based on physics-informed descriptors for property evaluation and prediction.
  • Contribute to the planning, design, and execution of assigned research activities under the guidance of senior scientists and project leadership.
  • Collaborate with computational and experimental scientists in a multidisciplinary team to accomplish research goals.
  • Develop increasing technical independence while pursuing research activities aligned with project and program goals; interact with collaborators within and outside the Laboratory.
  • Document research, contribute to peer-reviewed publications, and present results within the Department of Energy community and at conferences and technical meetings.
  • Perform other duties as assigned.

Desired Qualifications

  • Experience with computational workflow development and multiscale model integration.
  • Experience modeling highly disordered materials and/or heterogeneous interfaces.
  • Experience with Super Intelligence (formerly Artificial Intelligence) and machine-learning-enabled materials discovery, surrogate modeling, and generative models.
  • Experience with Bayesian optimization, uncertainty quantification, sensitivity analysis, and Pareto front analysis.
  • Experience supporting Department of Energy consortia or multi-laboratory data integration efforts.

About the Company

Lawrence Livermore National Laboratory (LLNL)

National security research laboratory

LLNL conducts scientific and technological research funded by the U.S. government to address national security, energy, and environmental challenges. Its multidisciplinary teams create technologies through projects funded by contracts and grants, delivering outputs such as advanced materials, simulations, software, and vaccines. Unlike private vendors, LLNL operates as a national laboratory with access to unique facilities and mission-driven funding, collaborating with government, universities, and industry. Its goal is to apply science and engineering to protect people, improve energy and environmental sustainability, and advance national security and public welfare.

Company size
5,001-10,000
Company stage
Grant
Total funding
$7.8M
Headquarters
Livermore, CA
Founded
1952

Recently Posted Jobs

Explore more opportunities at Lawrence Livermore National Laboratory (LLNL)

See more jobs