Principal Scientist, Oncology Data Science (Translational Science)

Experteer Overview In this role you will advance AI methods to predict how altering a tumor's molecular state changes clinical outcomes. You'll work at the intersection of machine learning, genomics, and real-world data, integrating multimodal datasets and applying causal inference. You'll collaborate with wet-lab scientists and clinicians to validate models and translate insights into asset prioritization and patient stratification. The position offers high-velocity research leadership within GSK's oncology data science team, contributing to patient-focused outcomes and publication activity. This role combines technical execution, leadership, and cross-functional communication to bring the right therapies to- Compensation / Benefits * Own the data pipeline and develop advanced ML architectures for multimodal datasets (single-cell, spatial omics, histopathology, functional genomics, real-world data) * Collaborate with wet-lab scientists, clinicians, and pathologists to validate models, including in-silico perturbations within the tumor microenvironment * Develop interpretable features from models to generate testable oncological hypotheses and guide clinical pipeline decisions * Contribute clean, reproducible tooling to cross-team frameworks with good engineering practices (architecture planning, clean code, automated testing) * Stay updated on advances and share knowledge, contributing to publications and external engagement Tasks * PhD (or equivalent) in a quantitative field with 1+ years industry/post-doc experience * Experience in cancer/computational biology with understanding of tumor microenvironment dynamics and high-dimensional data * Statistical and machine learning expertise * Experience with single-cell omics data analysis * Experience with statistical modelling of functional genomics or spatial omics datasets * Proficiency in Python and deep learning frameworks (PyTorch); strong software engineering fundamentals (version control, modular design, CI/CD) Key requirements * annual bonus * long-term incentive program * health care and other insurance benefits * retirement benefits * paid holidays * paid caregiver/ parental and medical leave

outcomes in-silico perturbations within the tumor microenvironment * Develop interpretable features from models to generate testable oncological hypotheses and guide clinical pipeline decisions * Contribute clean, reproducible tooling to cross-team frameworks with good engineering practices (architecture planning, clean code, automated testing) * Stay updated on advances and share knowledge, contributing to publications and external engagement Tasks * PhD (or equivalent) in a quantitative field with 1+ years industry/post-doc experience * Experience in cancer/computational biology with understanding of tumor microenvironment dynamics and high-dimensional data * Statistical and machine learning expertise * Experience with single-cell omics data analysis * Experience with statistical modelling of functional genomics or spatial omics datasets * Proficiency in Python and deep learning frameworks (PyTorch); strong software engineering fundamentals (version control, modular design, CI/CD) Key aa leadership * annual bonus * long-term incentive program * health care and other insurance benefits * retirement benefits * paid holidays * paid caregiver/ parental and medical leave