Senior Expert Data Scientist Translational Medicine data42

Job Description Summary

Do you love data and technology? Are you passionate about AI and eager to explore its potential? Are you a team-player who inspires greatness in others? Do you want to contribute to the research and development of innovative medicines that address society’s greatest disease burdens and restore possibility for patients?

Join our data42 team!

At Novartis, we reimagine medicine by using the wealth of our internal data combined with advanced analytics and modeling. Our data42 platform provides access to Novartis’s high-quality, multi-modal preclinical and clinical data (as well as external/licensed data). It is the perfect environment to develop cutting edge AI/ML models. At data42, we are a global team of data scientists and data engineers dedicated to uncovering novel insights and to drive drug development pipeline decisions by leveraging the data42 platform.

data42 is currently seeking a highly skilled individual to join our team as a Data Science Expert. As an essential part of the team, you will collaborate with scientists in various disease and functional areas across the organization to advance research and drug development, specifically in Translational Medicine (TM).

Together with the data42 Translational Medicine (TM) Scientific Lead, you will be part of our data42 Data Science function. Ideally you have prior experience with predicative safety and efficacy modeling using preclinical and clinical study data. You will collaborate with Scientists, Clinicians, Data Scientists, Toxicologists, Pathologists in the Translational Medicine area and with our colleagues in the AICS (AI and Computer Science) team.
  

 

Job Description

Major accountabilities:

• Leading data science projects and effectively communicating results/findings with stakeholders and collaborators. 
• Work collaboratively to develop or leverage cutting-edge AI/ML and Pharmacokinetics/Pharmacodynamics (PK/PD) models for predicting safety and efficacy
• Develop an in-depth understanding of the data and perform data wrangling for use case specific modeling and analytics tasks.
• Actively investigate safety signals leveraging preclinical and clinical data with forward and back translational methodologies to provide actionable insights to support decision-making.
• Independently develop, utilize, and enhance bioinformatics tools and models specifically designed for integrating diverse data types, enabling translational research and analysis.
• Acting as a connector between valuable data resources and project teams, enhancing the generation of hypotheses by sharing insights derived from preclinical and clinical study data.  

Requirements:

• Solid scientific research background, demonstrated ability to ask and answer critical questions using data and AI/ML 
• Effective at communicating and presenting scientific ideas and results to a diverse audience, including peers, stakeholders from different fields, and non-experts 
• Track record of rapidly upskilling in new subject areas to reach a high level of competence. Demonstrated a strong willingness to learn and step out of the comfort zone 
• Education: PhD in a quantitative field such as Computer Science, Physics, Statistics, Data Science, Mathematics or related quantitative field with experience in ML/AI 
• Understanding of disease biology preferred 

Preferred Technical Skills

• Programming & Tools: Python (NumPy, Pandas, Scikit-learn, TensorFlow, PyTorch), R, Spark, Git, Docker, good coding practices (e.g. version control, documentation), High-performance computing (HPC) 
• Data Engineering for analysis/modeling: Data cleaning and preparation, model deployment and optimization, processing big data (e.g. with Spark) 
• Machine Learning & Data Science: Supervised and unsupervised learning (e.g., Gaussian Mixture Models, DBSCAN, Random Forest), Deep learning (e.g. Neutral Networks, Transformers), Feature engineering, Dimensionality reduction (PCA, t-SNE, UMAP), Outlier detection, Statistical methods for inference, prediction and hypothesis testing (e.g. linear and logistic regression), and Data visualization 
• Experience with preclinical and clinical study data. Other related data modalities (e.g. ECG, omics, etc…) would be a plus. 
• Ability to communicate complex analyses and findings to a diverse audience, including effective data visualization.  
• Strong scientific curiosity, initiative, and learning agility. 
• Ability to work as part of an interdisciplinary team, including clinicians, biologists, toxicologists, pathologists, and data scientists.