Job Description Summary

The Data Scientist will work alongside quantitative scientists, domain experts and product developers to ensure teams succeed in answering scientific questions using the data42 platform. They will help our users to apply and develop analytical methods and predictive models that deliver impact on research and drug development programs. Furthermore, they will collaborate on analytical pipelines (e.g. for imaging or omics) that can be re-used across the platform. Within the project and when working with our users, data42 data scientists will develop and advocate for good data science practices. data42 Data Scientists will also contribute to the design of our platform, to make it accessible, useful and an appealing toolset for the whole data science and AI community at Novartis.

We are looking for a data scientist bringing expertise in two or more of the following areas:

• Analysis of omics data of various modalities
• Experience with data from CRM (Cardiovascular, Renal, Metabolism).
• Applied/computational data science and large-scale / ‘big data’ computation,
• Development and management of disease area focused data pools
• Biostatistics for the analysis of clinical data (SDTM/ADAM) and/or RWE data
• Machine learning / deep learning and large language models

Job Description

Your responsibilities will include, but are not limited to:

• Ensure that scientific teams are enabled and supported to achieve their goals at data42.
• Contributes to the acceleration of data science through activities such as the development of reusable pipelines for the data preparation and analyses. 
• Develops frameworks for generation and reporting of key results, quality benchmarks for data, models, and impact in collaboration with our data scientist users.
• Applies their expertise in machine learning, deep learning, data visualization and structured/unstructured data analytics towards the scientific goals of their team.
• Acts as an advocate for good data science practice across data42.

Desirable additional skills in two or more of the following areas:

• Knowledge of CDISC data standard (SDTM, ADaM)
• Experience with pooling of clinical trial data
• Understanding of the drug discovery and development process
• Experience working in the field of CRM (Cardiovascular, Renal, Metabolism).
• Experience with computational environments for large-scale data science (e.g. high-performance computing or Spark),
• Statistical and machine learning, and / or applied deep learning methods for time series data.
• Experience in using the Foundry platform for data analysis.

Minimum Requirements:

• Preferably Ph.D. in scientific or relevant discipline or equivalent.
• At least 2 years of professional experience in the pharmaceutical sector
• Experience with bioinformatics (around DNA / RNA / proteomics data analysis) and/or statistical genetics and/or biostatistics.
• Strong experience with R or python for data analysis and statistical modelling
• Experience in using machine learning models to predict clinical endpoints using multimodal data.
• Experience with use of AI/GenAI/LLMs for automating or accelerating data- or data science related processes.
• Experience with the principles and tools of good data science practice (e.g. git/versioning).
• Excellent communication and stakeholder management skills

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