Machine Learning Scientist

Job Summary

To support the PFAS substitution program, the full-time remote Machine Learning Scientist will design and run high-throughput quantum chemistry simulations, develop machine learned force fields, and collaborate with cross-functional teams to validate and deploy models for predicting molecular properties.

Key Responsibilities

• Design and execute high-throughput physics-based simulation campaigns to generate labeled training data for PFAS chemical space
• Develop and maintain automated workflows for data generation and curation, ensuring reproducibility and version control
• Train, validate, and deploy machine learned interatomic potentials while collaborating with various teams to ensure model accuracy and usability

Required Qualifications

• PhD in Computational Chemistry, Materials Science, Physics, Machine Learning, or a related field with specialization in machine learned interatomic potentials
• Experience developing and deploying machine learned force fields, including training and validation of at least one potential
• Hands-on experience with quantum chemistry and electronic structure codes for generating first principles training data
• Strong programming skills in Python and experience with modern ML frameworks such as PyTorch or JAX
• Practical experience coupling learned potentials into molecular dynamics engines and extracting physical observables