Senior ML Scientist: Accelerate Drug Discovery with AI

Revolution Medicines; San Francisco (CA); On-site; USD 251,000 - 295,000; Full time

Job summary

Revolution Medicines seeks a Senior Machine Learning Scientist to accelerate drug discovery by building predictive models that transform complex biological and chemical data into actionable insights. You will operate at the interface of data science, chemistry, and biology, collaborating closely with experimental teams to guide research decisions.

Key tasks include developing models for activity, selectivity, ADME/Tox, and translational research, while leveraging deep learning, graph neural

Qualifications

• PhD in a quantitative field with strong ML focus.
• 6–10 years applying ML to scientific data.
• Proficiency with Python scientific stack.
• Experience with PyTorch, TensorFlow or scikit-learn.
• Experience handling noisy biological/chemical data.

Responsibilities

• Develop predictive models for drug discovery and compound activity.
• Design and implement ML models for ADME/Tox and target engagement.
• Apply deep learning, graph networks, and ensemble methods.
• Evaluate models and validate with appropriate strategies.
• Collaborate with data/ML engineers to deploy in pipelines.
• Analyze complex chemical, biology, and phenotypic data.
• Integrate diverse datasets including chemical, structural biology data.

Skills

PhD in ML/quant field

6–10 years ML in science

Python & NumPy/Pandas/SciPy

ML frameworks (PyTorch, TensorFlow)

Model dev, validation & eval

Data visualization & EDA

Handling noisy datasets

Education

PhD in ML/comp biology/comp chem/CS

Tools

RDKit

OpenEye

Job description

Revolution Medicines seeks a Senior Machine Learning Scientist to accelerate drug discovery by building predictive models that transform complex biological and chemical data into actionable insights. You will operate at the interface of data science, chemistry, and biology, collaborating closely with experimental teams to guide research decisions.

Key tasks include developing models for activity, selectivity, ADME/Tox, and translational research, while leveraging deep learning, graph neural