Computational Materials Science Expert

This is a remote, project-based role for machine learning professionals with deep expertise in computational materials science. You will complete tasks at the intersection of ML and materials research — including model development, simulation data analysis, and research tasks applied to real atomistic, electronic, or structural materials datasets. Work is over the next 2–3 weeks, asynchronous, and assigned on a project-by-project basis, with an expected commitment of 10–20 hours per week for the projects you accept. This position offers exceptional pay, exposure to cutting-edge materials research problems, and a strong addition to your research portfolio.

Responsibilities

• Apply machine learning techniques to materials science problems, including property prediction, materials discovery, and structure-property relationship modeling
• Build, train, and evaluate ML models trained on simulation data such as DFT, molecular dynamics, or Monte Carlo outputs
• Develop predictive models using supervised and unsupervised learning approaches relevant to materials systems
• Contribute to materials informatics workflows integrating ML with high-throughput computational pipelines
• Document methodologies, model assumptions, and technical approaches clearly and reproducibly

Requirements

• Published researcher with at least one first-author publication in a peer-reviewed journal
• Demonstrated expertise in both machine learning and computational materials science (e.g., DFT, force field development, atomistic simulation, or materials informatics)
• Strong problem-solving skills and ability to work independently on technical tasks
• Master's or PhD in Materials Science, Computational Chemistry, Physics, Computer Science, or a related quantitative field

Preferred qualifications

• Background in TA'ing or teaching computational physics, chemistry, or materials science courses
• Familiarity with materials-focused ML frameworks (e.g., CGCNN, MatGL, M3GNet, ALIGNN, or similar graph neural network approaches)
• Experience with computational materials tools and frameworks (e.g., VASP, Quantum ESPRESSO, LAMMPS, ASE, or similar)