Data Scientist # 4740

We are seeking a Data Scientist with strong expertise in cancer genomics and omics data modeling to help us drive the next wave of innovation in early cancer detection.

In this role, you will analyze some of the world’s largest and richest genomic and real-world datasets to uncover biological signals, model cancer biology, and identify genomic features that improve test performance. You will apply cutting-edge statistical and machine learning methods to extract biological insights from complex multi-omic datasets and translate them into actionable improvements and new products for clinical oncology applications.

The ideal candidate combines deep knowledge of cancer genomics with practical experience in statistical inference and machine learning model development. You will work cross-functionally with computational biologists, assay scientists, machine learning and data engineers, and clinical experts to accelerate innovation, strengthen test performance, and discover cancer biology.

This role is based in Menlo Park, California, and will move to Sunnyvale, California, in Fall 2026. It offers a flexible work arrangement, with the ability to work from GRAIL's office or from home. Our current flexible work arrangement policy requires that a minimum of 40%, or 16 hours, of your total work week be on-site. Your specific schedule, determined in collaboration with your manager, will align with team and business needs and could exceed the 40% requirement for the site. At our Menlo Park campus, Tuesdays and Thursdays are the key days where we encourage on-site presence to engage in events and on-site activities.

Responsibilities:

• Analyze and interpret large-scale NGS datasets to identify biological and molecular patterns of cancers related to cancer detection
  
  

• Design, implement and validate innovative statistical methods and machine learning models to extract and interpret cancer genomic signals for product innovation
  
  

• Work closely with interdisciplinary teams (computational, clinical, assay development, and product) to translate data-driven insights to actionable decisions
  
  

• Present and communicate high-quality, evidence-based research findings with clarity and rigor

Required Qualifications:

• Ph.D. in Cancer Genomics, Statistics, Bioinformatics, Computational Biology, Data Science, Engineering or a related field.

• Proven track record in working with large-scale omics datasets in R or Python.

• Proven expertise in cancer genomics — excellent knowledge of cancer biology, tumor genetics, and molecular mechanisms of oncogenesis.

• Familiarity with NGS data processing, statistical modeling, and machine learning frameworks (e.g., scikit-learn, TensorFlow, PyTorch).

• Excellent communication, collaboration, and problem-solving skills; ability to work effectively in interdisciplinary environments.
  
  

Preferred Qualifications:

• Experience in hematological oncology research

• Knowledge of cancer epigenetics

• Demonstrated ability to integrate biological knowledge with computational modeling to uncover new insights or create new computational tools/methods.

• Deep understanding of modern machine learning fundamentals and AI techniques for genomics applications, including model development, evaluation, and interpretation.

• Experience with deep learning and/or large language model (LLM) training or adaptation.

• Proficiency in Python or R, with experience in modern data science workflows (Linux, versi