Data Scientist

Sanofi is hiring a Data Scientist for a 6-month contract with the Quantitative Pharmacology (QP) group. This onsite role in Cambridge, MA supports drug discovery and development through PK/PD modeling, scientific data analysis, and decision-support computational solutions. You will build tools that are robust, validated, reproducible, and designed to be user-friendly for QP scientists.

Responsibilities

• Develop and enhance PK/PD models and quantitative pharmacology tools
• Conduct scientific data analysis, visualization, and model diagnostics
• Create interactive applications using Python and Shiny for Python
• Build automated, reproducible analytical workflows
• Develop mathematical and machine learning models to support compound prioritization and early drug development decisions
• Integrate molecular structures, compound descriptors, experimental data, and related information to predict pharmacokinetic and pharmacological properties of small molecules
• Explore AI-enabled and agentic workflows to automate and orchestrate data analysis, model execution, interpretation, and reporting
• Support computational solutions across multiple therapeutic areas and research platforms within Sanofi’s broader R&D organization
• Work closely with QP scientists to advance PK/PD modeling, analysis, and decision-support tools for drug discovery and development
• Deliver computational solutions that are validated, reproducible, and user-friendly

Requirements

• Bachelor’s degree or higher in Computer Science, Engineering, Data Science, Applied Mathematics, or a related quantitative field
• 1–3 years of relevant professional experience
• Strong background in software development and scientific computing
• Proficiency in Python
• Some experience building interactive applications using Shiny for Python or related frameworks
• Familiarity with software development practices, including Git, testing, documentation, and reproducible workflows
• Experience with scientific data analysis, visualization, and mathematical/statistical modeling
• Familiarity with machine learning model development, evaluation, and validation
• Experience with or familiarity with ML libraries/frameworks such as scikit-learn, PyTorch, TensorFlow, or Keras
• Ability to work effectively in a matrixed and global environment

Preferred Qualifications

• Familiarity with PK/PD modeling
• Experience with dynamical systems, time-series, or longitudinal data
• Experience working with molecular structures, compound descriptors, or experimental drug-development data
• Familiarity with AI-enabled or agentic workflows for automating and orchestrating data analysis, model execution, interpretation, and reporting
• Experience in pharmaceutical, biotechnology, drug discovery, or related scientific research environments

Technology stack: Python, Shiny for Python, Git, scikit-learn, PyTorch, TensorFlow, Keras.