Postdoctoral Fellow, Machine Learning Force Fields

We’re seeking a Postdoctoral Fellow in Machine Learning (ML) to join us in our mission to improve human health and quality of life through the development, distribution, and application of advanced computational methods.  As a member of our Materials Science team, you’ll develop state-of-the-art ML force fields which will be applied to impactful applications in materials sciences.

Who will love this job:

• A machine learning enthusiast with a background in physical science
• An innovator who’s driven to leverage technical knowledge to make a tangible impact
• A scientist with deep knowledge of both finite system and periodic DFT, as well as other electronic structure methods, and who understands the limitations and appropriate applications of these methods
• A proficient Python programmer who can write their own scripts
• An independent researcher who enjoys collaborating with an interdisciplinary team in a fast-paced environment

What you’ll do:

• Build and manage large data sets generated using quantum chemical methods at scale to develop predictive ML force fields
• Develop software that trains and applies ML force fields to challenging problems in materials sciences
• Extend the accuracy, capability and generalization of current ML force fields
• Communicate results and present ideas to the team

What you should have:

• A PhD (or extensive experience) in Chemistry, Materials Science, Engineering, Computer Science, or Physics
• A proven track record of scientific contribution and independent research
• Prior experience with development of ML force fields and/or electronic structure methods 
• Experience with predicting electronic properties using VASP, Quantum ESPRESSO, or similar modeling software
• Prior knowledge of ML toolkits such as Scikit-Learn, NumPy, SciPy, Pandas, and PyTorch is a plus, but not required
• Understanding of surface chemistry is a plus, but not required