Scientific Technical Lead, Early Stage PDST CMC

What you'll do

• Develop and deploy predictive models to support process development decisions for early-stage biologics.
• Design hybrid modeling approaches that combine first-principles process understanding with data-driven techniques.
• Build analytical frameworks to support digital twin concepts and in-silico process optimization.
• Define data strategies for new programs, including data collection, structuring, and integration across experimental campaigns.
• Architect AI-driven workflows using machine learning, statistical methods, or orchestrated AI pipelines based on scientific needs.
• Design statistically rigorous experiments using DoE, Bayesian optimization, and active learning strategies.
• Identify and characterize critical process parameters (CPPs) and their relationships to critical quality attributes (CQAs).
• Translate complex quantitative analyses into actionable insights for scientists, engineers, and senior leadership.

What we're looking for

• Bachelor’s degree in computer science or related field with 7 years experience, Master's with 6 years, or PhD with 2 years in IT or application development.
• Hands-on experience building and deploying data science or machine learning solutions in scientific or engineering-intensive environments.
• Expert-level Python proficiency including the scientific ecosystem (NumPy, pandas, scikit-learn, PyTorch/TensorFlow) and modern data engineering.
• Mastery of business analytics tools including R, Dataiku, AWS SageMaker, Spark, and Tableau.
• Experience with design of experiments (DoE), Bayesian methods, or active learning in scientific applications.
• Experience applying data science in a GxP-regulated environment with knowledge of FDA/EMA expectations for process validation and control strategy.
• Familiarity with MLOps principles, model lifecycle management, or deployment of analytical tools in regulated or enterprise environments.
• Advanced degree in Data Science, Biostatistics, Chemical/Biochemical Engineering, or Computational Biology (preferred).