Machine Learning Scientist II, Drug Discovery Analytics

Scorpion Therapeutics; California (MO); On-site; USD 120,000 - 180,000; Full time

Job summary

Revolution Medicines is seeking a Machine Learning Scientist II to advance drug discovery through predictive modeling across biological, chemical, and imaging datasets. You will collaborate with chemists, biologists, and data engineers to weave ML into discovery workflows and ensure methods are well documented for reproducibility.

The role emphasizes developing, evaluating, and implementing models that accelerate targeting and compound optimization in oncology-related projects.

Qualifications

• PhD or MS in ML, computational biology/chemistry, or related field.
• 2–5 years applying ML to scientific datasets.
• Strong Python skills and experience with ML frameworks.

Responsibilities

• Develop, evaluate, and implement predictive models across biological, chemical, and imaging datasets.
• Perform exploratory data analysis to guide modeling decisions.
• Collaborate with chemists, biologists, and data engineers to integrate models into discovery workflows.
• Document methods and results to ensure reproducibility.

Skills

Python

Machine Learning

PyTorch

TensorFlow

Scikit-learn

Data Wrangling

Computational biology

Education

PhD or MS in ML or computational biology

Tools

RDKit

Job description

Role: Machine Learning Scientist II supporting drug discovery at Revolution Medicines, focusing on advanced analytics and AI to accelerate targeting and compound optimization for RAS-addicted cancers.

Responsibilities: develop, evaluate, and implement predictive models across biological, chemical, and imaging datasets; perform exploratory data analysis; collaborate with chemists, biologists, and data engineers to integrate models into discovery workflows; document methods for reproducibility.

Requirements: Ph.D. or M.S. with relevant experience in machine learning, computational biology/chemistry, or related fields; 2-5 years applying ML to scientific datasets; strong Python skills; experience with frameworks like PyTorch, TensorFlow, scikit-learn; capable of working with noisy experimental data.

Preferred: biotech/pharma experience, familiarity with phenotypic screening, cheminformatics tools like RDKit, and multi-omics data analysis.

High-Value: focus on oncology (RAS-driven cancers), drug discovery, predictive modeling, imaging, phenotypic profiling, and integration with biological interpretation.

Work setup: not specified.