Machine Learning Scientist I/II, Chemistry

Role overview: Define and implement models that reason through the physical rules governing chemistry to predict physiochemical interactions at the molecular level. Lead building a chemistry discovery platform from scratch and serve as the computational visionary. Responsibilities include developing models that predict phase behaviors and properties of chemical mixtures across temperature, hydration, and concentration gradients; constructing a generative lab-in-the-loop modeling pipeline that incorporates formulation scientist input and experimental feedback to propose next tests in the wet lab; leveraging next-generation chemistry ML methods such as chemical LLMs, reaction prediction, and electronic structure methods (DFT); owning the data flow pipeline, including data standards, processing, data distribution analysis, and visualization to guide decisions. Qualifications include PhD (or equivalent) in ML, computational chemistry, organic chemistry, chemical engineering, materials science, or related field; strong experience building and validating ML models in chemistry or related domains; knowledge of fundamentals of chemical properties; proficiency with Python-based DL frameworks (PyTorch, PyTorch Lightning), ML logging (MLFlow, WandB), RDKit, Optuna; ability to set up and maintain Python compute environments; strong code organization and reproducibility practices with git-based workflows; familiarity with cloud/HPC (AWS, Azure), Docker, and batch compute; experience handling large, noisy experimental datasets; strong teamwork and cross-functional communication; preferred experience with DFT and molecular dynamics, Bayesian optimization/active learning/reinforcement learning, lab-in-the-loop platforms, and thermodynamics/phase-diagram analysis.