PhD in machine learning, computational materials science, or related area, or comparable industry experience.
Experience in developing machine learning force fields.
Proficiency in collaborative code development in Python on shared codebases.
Publication track record in relevant academic journals (npj computational materials, PRB, PRL, etc.) or top-tier conferences (NeurIPS, ICML, ICLR, etc.).
Ability to work in an interdisciplinary collaborative environment, through effective communication of technical concepts tonon-experts from different technical backgrounds.
Preferred:
Experience in developing large scale foundational machine learning force fields.
Experience in evaluating machine learning force fields for real-world tasks.
Experience in designing and producing large scale datasets for machine learning force fields.
Responsibilities
Design and implement novel neural network architectures for training foundational machine learning potentials.
Improve the inference speed of machine learning potentials and scale them to large systems.
Design and implement pipelines to evaluate machine learning potentials for real-world tasks.
Design and generate novel datasets for training foundational machine learning potentials.
Prepare technical papers, presentations, and open-source releases of research code.