Machine Learning Scientist II

Revolution Medicines•Redwood City, CA

15h•$202,000 - $238,000•Onsite

About The Position

Revolution Medicines is a global, commercial-stage oncology company dedicated to discovering, developing, and delivering innovative medicines for patients with RAS-addicted cancers. Leveraging its differentiated RAS(ON) tri-complex inhibitor platform, the company is advancing a broad, integrated portfolio of oral RAS(ON) inhibitors designed to directly target the active, cancer-driving state of RAS. Founded on rigorous scientific inquiry and a willingness to challenge long-held assumptions, Revolution Medicines is committed to changing the trajectory of disease for patients with RAS-addicted cancers worldwide. Our people are united by a shared way of working: follow the science, challenge assumptions, act with urgency, and hold ourselves to a high standard of rigor—all in service of patients. We are seeking a Machine Learning Scientist II to help accelerate drug discovery through advanced analytics and artificial intelligence. This hands-on individual contributor will develop and apply predictive models and analytical methods that transform complex biological and chemical datasets into actionable insights for research teams. The Machine Learning Scientist II will work at the interface of data science, chemistry, and biology to support target discovery, compound optimization, phenotypic screening, and translational research. The role is well-suited to a scientist who brings strong technical foundations in machine learning, curiosity about drug discovery, and a collaborative approach to solving real-world scientific problems. Working with senior data scientists and experimental collaborators, the successful candidate will contribute analyses, models, and reusable workflows to a data-driven discovery ecosystem where data, analytics, and experimentation continuously inform one another.

Requirements

Ph.D. in machine learning, computational biology, computational chemistry, computer science, statistics, bioinformatics, or a related quantitative field; or a M.S. degree with relevant industry experience.
Typically 2-5 years of relevant experience applying machine learning, data science, or advanced analytics to scientific datasets; relevant doctoral research may be considered.
Demonstrated experience developing, validating, and evaluating predictive or classification models.
Strong Python programming skills and experience with scientific computing libraries such as NumPy, Pandas, and SciPy.
Hands-on familiarity with machine-learning frameworks such as PyTorch, TensorFlow, and/or scikit-learn.
Experience with data visualization, exploratory data analysis, and working with noisy or incomplete experimental datasets.
Ability to communicate technical work clearly and collaborate effectively with cross-functional scientific partners.

Nice To Haves

Experience in biotechnology, pharmaceutical, healthcare, or drug discovery environments.
Experience with phenotypic screening, high-content imaging, Cell Painting, morphological profiling, or computer vision for microscopy images.
Familiarity with representation learning, self-supervised learning, embedding generation, dimensionality reduction, clustering, or phenotype discovery.
Familiarity with cheminformatics or molecular modeling tools, such as RDKit or OpenEye.
Experience with multi-omics data analysis, cloud computing environments, MLOps, or scalable model deployment.
Working knowledge of cell biology, drug discovery workflows, assay development, microscopy, experimental design, or biological interpretation of machine-learning results.

Responsibilities

Develop, implement, and evaluate machine-learning models that support drug discovery questions, including compound activity, selectivity, developability, target engagement, and phenotypic screening outcomes.
Perform exploratory data analysis and quality assessment on chemical, biological, imaging, and phenotypic datasets.
Prepare and integrate heterogeneous datasets, including chemical structure and screening data, structural biology outputs, molecular simulation outputs, and high-content imaging or morphological profiling data.
Apply appropriate modeling approaches, including supervised learning, deep learning, graph-based methods, and ensemble methods, under the guidance of project and functional leads.
Use sound validation strategies to assess model performance, robustness, applicability, and limitations.
Collaborate with data engineering and machine-learning engineering partners to support reproducible workflows and integration of analytical outputs into discovery pipelines.
Partner with medicinal chemists, biologists, and other research scientists to translate scientific questions into computational analyses and communicate results clearly.
Document methods, code, results, and key assumptions in a manner that supports reproducibility and knowledge sharing.