Data Scientist – Machine Learning

Job Responsibilities

• Design, build, and iteratively refine novel machine learning models using modern architectures and classical statistical methods to address translational oncology questions.
• Develop and apply multi-modal modeling approaches integrating RNA-seq expression data with mutations, copy number alterations, fusions, protein markers, and clinical metadata.
• Translate model outputs into improvements on the Caris clinical diagnostic platform to support improved treatment predictions.
• Publish results in peer-reviewed journals and present findings at scientific conferences and internal forums.
• Support collaborations with biopharma partners by providing analytical expertise, developing custom analyses, and communicating results to external stakeholders.
• Stay current with advances in machine learning research, tools, architectures, and emerging development paradigms.

Required Qualifications

• Ph.D. in Computer Science, Computational Biology, Applied Mathematics, or a related quantitative field; or M.S. degree with 3+ years of relevant professional experience.
• Deep familiarity with modern machine learning approaches including representation learning, attention-based architectures, foundation models, and self-supervised learning.
• Working knowledge of statistical modeling concepts relevant to clinical data, including generalized linear models, survival analysis, and Bayesian methods.
• Demonstrated experience building and applying novel machine learning models beyond off-the-shelf solutions.
• Proficiency in Python and the scientific computing ecosystem (PyTorch or TensorFlow, scikit-learn, pandas, NumPy, SciPy).
• Strong written and verbal communication skills.
• Familiarity with Linux environments and Git.
• Proficient in Microsoft Office Suite including Word, Excel, Outlook, and business internet tools.

Preferred Qualifications

• Understanding of cancer and molecular biology with experience using large-scale genomics datasets.
• Peer-reviewed publications in machine learning or computational biology.
• Experience with computer vision for digital pathology.
• Experience with natural language processing of EHR or real-world data.
• Experience deploying models in cloud environments and MLOps practices.