Research Engineer - AI for Chemistry

Meta's Fundamental AI Research organization (FAIR) is developing AI-based methods to accelerate novel material discovery. In this position you will be joining the AI for Chemistry team doing this work. The material domains currently being worked on are electro-catalysts for CO2RR & OER, nano-porous materials for direct air capture, and new materials for display technologies.

You will be a researcher for AI modeling of crystalline materials. The role will be performed in close collaboration with computational and experimental chemists in Reality Labs Research and AI researchers in FAIR. You will be expected to provide technical leadership across large-scale ab-initio simulations, data generation and management for ML training, ML modeling, and applying ML models to material discovery.

The work being done will in some cases be published and open-sourced. This role may also be done jointly with various university academic collaborators. The aim of the work is to go end to end from computational discovery to productizing new materials, so you will have the opportunity to work across that entire lifecycle.

Research areas may include Machine Learning, Graph Neural Networks, Graph learning, Density Functional Theory, Computational chemistry, Optics, or other similar fields.Currently has, or is in the process of obtaining a Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience. Degree must be completed prior to joining Meta 1+ year of industry experience in Machine Learning, Graph Neural Networks, Graph learning, Density Functional Theory, Computational chemistry, Optics, or other similar fields. Research and engineering experience in Machine Learning or Artificial intelligence. Interest and experience with computational chemistry, material science, or scientific domains. Experience collaborating with partner teams. PhD in Computer Science, Materials Science, Machine Learning, or similar fields of study. Publications in machine learning Experience building very large ab-initio simulation datasets Experience testing and validating large AI/ML models for inorganic materials science