Senior Expert Data Scientist - Translational Medicine

As a member of the Quantitative Sciences & Innovation (QSI) unit in Biomarker Development, you will join Novartis’ clinical trial teams to speed new medicines into the clinic across one of the industry’s largest and most innovative portfolios. By integrating high-throughput biomarker technologies from First in Human through Phase III clinical trials, you will investigate disease heterogeneity, drug efficacy, and patient safety at molecular resolution to advance trials in new indications and patient populations. You are a passionate and curious scientist, eager to bring creative solutions to biology’s most daunting challenges on our journey to reimagine medicine. Working alongside dedicated physicians and biomarker scientists in a global multi-disciplinary team, our Data Scientists provide the analytical insights that drive Translational success.

Major AccountabilitiesConceive, design, and execute exploratory analyses as Lead Data Scientist across First in Human, Phase I-III clinical trials, applying advanced analytical methods as required. Participate in and lead cross-functional biomarker collaborations with Discovery and Development partners to support target selection, clinical development, and registration activities.  Provide subject matter expertise for high-dimensional clinical data (genetics, omics, digital, and/or imaging) and analysis solutions to inform disease characterization, patient stratification and enrichment strategies. Contribute to shaping the Novartis’ data and digital strategy by adhering to rigorous data engineering principles to unlock AI-powered discoveries. Work expeditiously as a member of matrixed clinical trial teams with diverse membership and expertise.  Minimum requirements PhD, MD or equivalent experience in computational biology, bioinformatics, statistical genetics, biostatistics, applied machine learning or AI, data science or related field. 3 years' experience in analyzing large-scale biological datasets in a drug discovery/development or relevant academic setting. Expert knowledge of statistical programming in R and Bioconductor. Proficiency with Unix/Bash, Python, or similar scripting language a must. Strong grasp of human genomics and next generation sequencing technologies, including experience implementing reproducible and scalable pipeline workflows in an HPC or Cloud environment. Previous experience in single-cell and/or spatial transcriptomics data analyses, including TCR/BCR repertoire analysis at bulk and/or single-cell level. Strong understanding of biostatistics and machine learning, including longitudinal analysis. Experience with generative coding assistants, copilots and developer tools highly desirable. Excellent communication and ability to translate analytical concepts for diverse audiences and stakeholders.