Computational Scientist Lead - DBM

Computational Scientist Lead - DBM page is loaded## Computational Scientist Lead - DBMlocations:
Barcelona time type:
Vollzeitposted on:
Heute ausgeschriebentime left to apply:
Enddatum: 6. März 2026 (Noch 14 Tage Zeit für Bewerbung) job requisition :
R2843666#
** Computational Scientist Lead - DBM
**
* Location:

Barcelona
* At Sanofi, we chase the miracles of science to improve people’s lives. We believe our cutting-edge science and manufacturing, fueled by data and digital technologies, have the potential to transform the practice of medicine, turning the impossible into possible for millions of people. As one of the leading investors in life sciences, manufacturing and research and development, we focus on delivering new and better ways to address unmet medical needs.

Our products empower self-care, prevent and treat diseases, and help people live better.

The  R&D Data & Computational Sciences Team is a key team within R&D Digital, focused on developing and delivering Data and AI products for R&D use cases. This team plays a critical role in pursuing broader democratization of data across R&D and providing the foundation to scale AI/ML, advanced analytics, and operational analytics capabilities. Specifically, the Data for New Technologies group focusses on developing AI models to support initatives involving Digital Biomarkers, Spatial Transcriptomics, Digital Histopathology and other emerging data modalities.

As a Computational Scientist specializing in Digital Biomarkers, you will join a dynamic team committed to advancing strategic and operational digital priorities within R&D. In this role, you will analyze complex, multimodal patient data collected from digital sensors and wearables, integrate these data streams with clinical trial and disease outcomes, and develop robust models that extract clinically meaningful insights. You will contribute to the design and validation of digital biomarkers by creating algorithms that capture patient functioning in real-world settings and by building models that combine multiple data modalities (such as physiology, clinical, imaging, etc.)

to deepen disease understanding and support decision-making across programs.

You will have the opportunity to work across multiple digital biomarker initiatives, collaborating closely with clinical, operational, biostatistics, and data teams to transform raw patient-generated data into actionable scientific and clinical insights.##
** Key Responsibilities
*** Evaluate feasibility of developing digital biomarkers and analysis pipelines from complex sensor‑based patient data (e.g., wearables, smartphone sensors, passive monitoring).
* Conduct advanced analyses of high‑frequency, multimodal patient data to extract features related to physiology, behavior, function, and symptoms.
* Develop machine learning and statistical models to derive robust clinical measurements, including models that may combine multiple data modalities and link them to clinical outcomes.
* Integrate digital biomarker outputs with data from other R&D products, such as clinical trial datasets, disease progression models, or real‑world evidence sources.
* Communicate scientific results through clear visualizations, dashboards, and structured summaries that support decision‑making by clinicians, program teams, and leadership.
* Contribute to regulatory and medical submissions, ensuring models, analyses, and digital biomarkers meet appropriate scientific and quality standards.
* Drive publication of methodologies and results in scientific journals and conferences to advance the field of digital biomarkers and sensor‑based analytics.
* Contribute to data pipelines and features required to operationalize digital biomarkers at scale, partnering with data engineering and product teams.
* Provide scientific and analytical guidance to junior team members on study design, modeling strategies, feature engineering, and validation methodologies.
* Identify opportunities for innovation in digital endpoint development, multimodal modeling, and use of real‑world or continuous monitoring data.
* Collaborate on the development of ML algorithms for new and emerging data modalities…