Postdoctoral Scientist, Oncology Foundation Models

Key Responsibilities

In this role, you will join the Data, Data Science & AI organization within Johnson & Johnson Innovative Medicine and contribute to the development and evaluation of foundation models for oncology using large-scale omics and clinical datasets. The work will focus on leveraging single-cell, spatial, and other high-dimensional molecular data to better understand tumor biology, the tumor microenvironment, and clinically relevant disease mechanisms. You will work closely with Oncology Translational Research and cross-functional scientific teams to translate complex biological data into robust computational models and actionable insights.

• Collaborate with Oncology Translational Research to develop computational models that generate insights relevant to precision medicine and drug development.
• Analyze and integrate high-dimensional biological data, including single-cell and spatial transcriptomics, for model development, training, and validation.
• Develop and implement scalable statistical, machine learning, and deep learning approaches using large-scale transcriptomic and multimodal datasets.
• Design rigorous model evaluation strategies, including appropriate benchmarks, validation datasets, and biologically relevant performance metrics.
• Partner with experimental and translational scientists to design studies that enable robust evaluation and interpretation of computational predictions.
• Develop reproducible, modular, and scalable research code consistent with internal software engineering and data integrity standards.
• Communicate methods, model performance, and scientific findings through technical reports, presentations, and peer-reviewed publications.

Qualifications

• Ph.D. completed within the last three years in computer science, artificial intelligence, bioinformatics, computational biology, statistics, or a related quantitative field.
• Strong programming skills in Python; experience with R is desirable.
• Strong background in machine learning, deep learning, statistical modeling, or representation learning.
• Experience developing modular, scalable, and reusable software for computational research or AI/ML applications.
• Experience analyzing large-scale transcriptomic or other high-dimensional biological datasets.
• Demonstrated ability to develop and rigorously evaluate computational models.
• Strong research record, including peer-reviewed publications.
• Strong written and verbal communication skills, with the ability to communicate complex computational concepts to both technical and scientific audiences.

Preferred Qualifications

• Experience applying AI/ML methods to oncology, cancer biology, or drug discovery.
• Experience with single-cell RNA-seq, spatial transcriptomics, or multimodal biological datasets.
• Experience with foundation models, representation learning, transformers, or other large-scale deep learning architectures for biological data.
• Familiarity with cell therapy discovery and development.
• Experience working at the interface of computational modeling and experimental or translational biology.