Band Level 4 Job Description Summary The Senior Data Scientist & Scientific Software Engineer will join the Modeling & Simulation Data Science team within the Translational Medicine Unit to help advance data-driven drug discovery. The role is focused on transforming large-scale ADME, PK, and related experimental datasets into actionable insights through advanced analytics, machine learning, and robust software engineering. Partnering closely with pharmacokinetic sciences (PKS) scientists, Data & Digital teams, and cross-functional stakeholders, this position will drive the development of scalable analytical applications, reusable computational workflows, and decision-enabling in silico solutions that accelerate lead optimization and strengthen scientific decision making.
Key Responsibilities Act as a key Modeling & Simulation Data Science representative on discovery and lead optimization programs, contributing scientific and strategic input to project discussions and decisions.
Partner with Data & Digital and PKS wet- and dry-lab teams to identify priority gaps, clarify business needs, and translate them into high-impact analytical and computational solutions.
Design, build, and maintain scalable applications, workflows, and data pipelines that support scientific analysis and decision making across projects and modalities.
Develop, evaluate, and deploy machine learning and statistical models to uncover relationships between chemical structure and molecular or pharmacokinetic properties.
Apply data mining, visualization, and exploratory analysis to derive insight from complex experimental datasets and communicate findings clearly to diverse stakeholders.
Create and implement project- or modality-specific in silico models and data strategies that accelerate and streamline compound progression decisions.
Write production-quality code following strong software engineering practices, including version control, testing, documentation, and maintainability standards.
Lead or contribute to cross‑functional initiatives spanning data science, software engineering, and laboratory teams, ensuring delivery of fit‑for‑purpose solutions.
Promote the adoption and effective use of in‑house tools, applications, and data science methods to maximize impact across Translational Medicine and PKS.
Stay current with advances in AI/ML, statistics, and computational methods relevant to ADME, PK/PD, and drug discovery, and help bring appropriate innovation into practice.
Essential Requirements Advanced degree in a relevant scientific or quantitative field such as cheminformatics, bioinformatics, biomedical engineering, computational biology, computational chemistry, data science, AI/ML in life sciences, or a related discipline.
PhD with 5+ years or MSc with 8+ years of relevant work experience applying data science in drug discovery, translational research, or related scientific environments.
Strong expertise in machine learning, statistics, and reproducible data science workflows, with demonstrated ability to apply them to real scientific problems.
Proficiency in Python and/or R, with solid software development practices including version control, testing, documentation, and production‑quality coding standards.
Experience designing, developing, and deploying robust analytical applications, computational workflows, or machine learning systems in collaborative environments.
Demonstrated ability to work across multidisciplinary teams and translate complex analytical concepts into clear, actionable insights for scientists and stakeholders.
Strong communication, collaboration, and leadership capabilities, with the ability to influence decisions in cross‑functional settings.
Good understanding of drug discovery processes, with particular relevance to ADME, pharmacokinetics, pharmacodynamics, or related translational data domains.
Desirable Requirements Experience with discovery‑stage PK modeling, ADME data interpretation, or relating preclinical properties to in‑vivo pharmacokinetic behavior.
Familiarity with modern machine learning approaches such as deep learning, generative algorithms, or explainable AI in drug discovery contexts.
Experience with modern scientific software or web application development frameworks, including JavaScript‑based front‑end technologies (e.g., "Svelte").
Knowledge of SQL, databases, Linux‑based environments, and scalable data engineering patterns for scientific workflows.
Experience working with small molecules, peptides, RNAs, or other modalities in discovery‑stage data analysis.
Accessibility and accommodation Novartis is committed to working with and providing reasonable accommodation to all individuals. If, because of a medical condition or disability, you need a reasonable accommodation for any part of the recruitment process, or in order to receive more detailed information about the essential functions of a position, please send an e‑mail to inclusion.switzerland@novartis.com and let us know the nature of your request and your contact information. Please include the job requisition number in your message.
#J-18808-Ljbffr