Computational Science Lead

Sanofi•Toronto, ON

7d•CA$158,200 - CA$208,200•Onsite

About The Position

Join Sanofi in one of our corporate functions and you can play a vital part in the performance of our entire business while helping to make an impact on millions around the world. At Sanofi, we chase the miracles of science to improve people’s lives. Within Digital R&D, the Integrative Clinical Data (ICD) team builds AI-powered products that transform how clinical trials are designed, executed, and optimized. This role sits at the intersection of trial design, operational analytics, and AI-driven decision systems. You will lead the development of modeling and data frameworks that enable smarter trial design, real-time operational insights, and scalable analytics across clinical programs. You will work across end-to-end data flows - from raw clinical and operational data to production-grade AI models and agentic systems. Your work will span in-silico trial prediction, patient representation learning, disease progression modeling, clinical foundation models, with extensions into trial enrollment, site intelligence, probability of technical and regulatory success (PTRS) modeling, and end-to-end trial optimization with agents. As a Lead Computational Scientist, you will operate as a technical owner across initiatives, driving modeling strategy, ensuring scientific rigor, and enabling deployment of decision-grade insights into our Drug Development products.

Requirements

5+ years of experience in data science, machine learning, computational biology, or related quantitative fields, with demonstrated ownership of end-to-end analytical or modeling workflows
Advanced degree (Master’s or PhD) in a quantitative discipline (e.g., computer science, statistics, engineering, computational biology, applied mathematics)
Strong programming experience in Python (preferred), with deep familiarity in scientific computing and machine learning frameworks (e.g., PyTorch, scikit-learn)
Experience applying software engineering best practices to data and ML systems, including version control, testing, modular code design, and reproducible workflows
Experience developing or applying agent-based or AI-driven decision systems, integrating machine learning models, data pipelines, and reasoning workflows to support complex tasks (e.g., clinical trial operations, monitoring, or optimization)
Strong understanding of model validation, experimental design, and performance evaluation in real-world or clinical AI settings
Experience working with data pipelines and large-scale datasets, including preprocessing, feature engineering, and reproducible workflows
Ability to translate ambiguous business or clinical problems into structured analytical approaches
Strong communication skills, with the ability to convey complex technical concepts to both technical and non-technical stakeholders

Nice To Haves

Preference for a track record of publications or contributions to machine learning conferences (e.g., NeurIPS, ICML, ICLR, ML4H) or related journals
Preference for experience working with cloud platforms and data infrastructure (e.g., AWS, Snowflake, Spark/PySpark)
Proven experience developing and deploying machine learning models on complex biomedical or clinical datasets (e.g., EHR, clinical trials, real-world data, imaging, multimodal data)

Responsibilities

Lead development of end-to-end clinical AI workflows, spanning data ingestion, curation, feature engineering, modeling, validation, and deployment across clinical trial design, execution, and optimization use cases
Design, own and implement advanced modeling approaches for in-silico trial prediction, patient representation learning, disease progression modeling and other development AI use cases – with an evaluation first mindset
Translate clinical development questions into scalable computational solutions, partnering with clinical, biostatistics, and product teams to define appropriate modeling strategies and success criteria
Drive integration of models into production systems and decision workflows, collaborating with engineering teams to ensure robustness, scalability, and usability
Define and implement validation frameworks, including statistical evaluation, temporal validation, and alignment to clinical and regulatory expectations
Communicate insights through clear narratives, visualizations, and decision frameworks, enabling adoption by clinical teams, study leads, and senior leadership
Mentor and guide junior scientists, providing direction on modeling approaches, study design, and best practices in machine learning and data science
Contribute to scientific leadership and external impact, including publications, conference submissions (e.g., ML4H, NeurIPS, AMIA), and cross-industry/academia collaborations
Identify and drive innovation opportunities across clinical AI, multimodal modeling, and agent-based systems for trial operations
Stay current with advancements in machine learning, generative AI, and clinical data science, and help translate these into practical applications across the organization