Senior Data Scientist - (AI / ML Omics Data - Immunology)

Job Description Summary

The Immunology Disease Area in Biomedical Research at Novartis is seeking a senior data scientist with a strong background in machine learning (ML) to lead the analysis and interpretation of biomedical data using state-of-the-art artificial intelligence (AI) approaches, with the goal of advancing our drug discovery pipeline for immune-mediated diseases.


Our Data Science team focuses on the application of translational bioinformatics and data analytics to clinical and preclinical programs in rheumatology, dermatology and nephrology. We apply computational biology and machine learning approaches to multiple data types to enable strategies for disease understanding, target identification, biomarker discovery, indication selection, and patient stratification.

 

Job Description

Responsibilities:

• Lead the integration and analysis of multi-modal data such as genetics, bulk, single cell and spatial transcriptomics, proteomics, imaging, and clinical data to build predictive models for target discovery, compound prioritization, disease progression and treatment response.
• Develop and apply advanced ML and AI algorithms tailored to biomedical data, including deep learning models, to derive actionable insights from complex datasets.
• Develop scalable data pipelines and deploy ML models in production environments.
• Stay abreast of the latest advancements in ML and AI, and continually integrate new methodologies and technologies into research projects.
• Leverage collaborative interfaces across and outside of Novartis to maximize the impact of AI for Immunology.
• Communicate complex ML and AI concepts and findings effectively to a diverse audience through presentations and publications.

Qualifications:

• PhD in data science, machine learning, artificial intelligence, bioinformatics, computational biology, or a related field, with substantial postdoctoral experience in academia or the pharmaceutical industry.
• Solid understanding of biology and immunology, ideally with prior experience in translational research.
• Experience in the application of supervised, unsupervised, semi-supervised, self-supervised, reinforcement and/or transfer learning methods to high-dimensional biomedical data.
• A track record in the successful implementation of deep learning models such as convolutional, recurrent and graph neural networks, generative adversarial networks, autoencoders and transformers.
• Proven familiarity with omics data types such as genetics, bulk, single cell and spatial transcriptomics, and proteomics.
• Proficiency in R and/or Python for statistical programming, bioinformatics (e.g., Bioconductor, Seurat, Scanpy, scVI-tools), ML (e.g., caret, tidymodels, scikit-learn, PyTorch, TensorFlow), reproducible research (e.g., R Markdown, Jupyter Notebooks) and web app development (e.g., Shiny, Dash).
• Experience with the Linux command line, high-performance computing environments, and cloud computing platforms such as AWS, Microsoft Azure and Google Cloud.
• Excellent interdisciplinary communication skills and proficiency in English (oral and written).
   

Novartis is committed to building an outstanding, inclusive work environment and diverse teams representative of the patients and communities we serve

 

Skills Desired

Apache Hadoop, Applied Mathematics, Big Data, Curiosity, Data Governance, Data Literacy, Data Management, Data Quality, Data Science, Data Strategy, Data Visualization, Deep Learning, Machine Learning (Ml), Machine Learning Algorithms, Master Data Management, Proteomics, Python (Programming Language), R (Programming Language), Statistical Modeling