Applied ML Scientist (Staff / Principal)

What you'll do

• Assess model performance and utility with project teams, and coordinate with ML and engineering teams to resolve issues or add functionality.
• Validate predictions against project data and benchmarks, and help experimental colleagues interpret predictions and uncertainty.
• Curate training and validation datasets and contribute to experiments evaluating model changes and architectures.

What they ask for

• Track record using machine-learning methods to impact small-molecule drug discovery projects.
• Hands-on cheminformatics expertise with tools such as RDKit or OpenEye.
• Familiarity with experimental drug discovery assays and CADD workflows.
• Strong Python coding and practical applied-ML skills, such as scikit-learn or PyTorch; experience modeling and statistically validating small-molecule datasets.

Nice to have

• PhD in Cheminformatics, Computational Chemistry, Computer Science, or a related field, and publications applying ML to drug discovery.
• Expertise in graph neural networks, multitask modeling, active learning, or Bayesian optimization; experience with SQL databases and data pipelining tools.

Tools

RDKit, OpenEye, Python, scikit-learn, PyTorch, SQL

AI focus

Apply, evaluate, validate, deploy, monitor, and improve AI/ML models for molecular drug discovery; assess prediction quality and uncertainty and support model research and experiments.