We're looking for an Applied Machine Learning Scientist who will be hands-on using our ChemML platform to drive design on multiple therapeutic programs while directly contributing to the development of our ChemML platform and ML models. This role offers an opportunity to translate cutting-edge ML into real-world impact on drug discovery. This role will report to the Senior Manager, Molecular Machine Learning and is a flexible hybrid (2 days per week in office) or remote (1 week per quarter on-site) role.

Work with industry-leading ADMET/In Vivo PK datasets to train and finetune foundation chemistry AI models

Develop small molecule generative AI and enumeration methods conditioned using our ADMET/affinity models for multi-parameter optimization (MPO)

Collaborate with software engineering teams to build robust pipelines for active/iterative learning and automated DMTL cycles

Directly shape the roadmap for our ChemML platform's evolution

Collaborate cross-functionally with machine learning scientists, medicinal chemists, and computational chemists to design and prioritize novel compounds using model outputs

Apply predictive models and AI-enabled design methods to solve real molecular optimization challenges across multiple therapeutic programs

Track performance of our binding affinity, selectivity, and ADMET/PK models on discovery programs and translate those insights into model improvements

Communicate model capabilities, results, limitations, and recommendations clearly to diverse stakeholders in regular discovery team meetings