Scientific Data Modeler

Scientific Data Modeler

Our large pharmaceutical client in Malvern, PA is seeking a Scientific Data Modeler to join a growing modeling core focused on developing and deploying process models that accelerate scientific decision-making across Cell & Gene Therapy (CGT) development. This individual will partner closely with scientists and fellow modelers to translate scientific challenges into fit-for-purpose computational models that support process understanding, optimization, and future digital twin initiatives.

The ideal candidate combines strong modeling expertise with excellent communication skills, enabling them to understand scientific requirements, select the appropriate modeling approach, develop and validate models, and ensure successful adoption by end users.

Key Responsibilities:

• Develop, validate, and deploy deterministic models that describe biological, chemical, and physical processes, including process conditions, transport phenomena, shear, temperature gradients, and chromatography operations.
• Translate scientific questions and process challenges into effective modeling strategies and technical solutions.
• Partner directly with scientists and stakeholders to gather requirements, define model objectives, and ensure models are fit for purpose.
• Build and maintain reusable modeling components that contribute to larger digital twin and in silico process development initiatives.
• Evaluate scientific problems and determine the most appropriate modeling methodology, balancing model complexity, accuracy, and usability.
• Conduct model verification, validation, and performance assessments to ensure scientific rigor and reliability.
• Collaborate with other modelers within a centralized modeling organization to scale model development efforts across multiple scientific programs.
• Publish, document, and deploy models for operational use, ensuring successful adoption by scientific users.
• Gather user feedback, refine model performance, and continuously improve deployed solutions.
• Support the evolution of empirical, PAT-enabled, machine learning, and AI-driven models as data availability increases.
• Contribute to gap assessments that identify high-priority modeling opportunities and accelerate scientific impact.