Scientific Technical Lead, Early Stage PDST CMC

Company Description

About Abb Vie

Abb Vie's mission is to discover and deliver innovative medicines and solutions that solve serious health issues today and address the medical challenges of tomorrow. We strive to have a remarkable impact on people's lives across several key therapeutic areas including immunology, oncology and neuroscience - and products and services in our Allergan Aesthetics portfolio. For more information about Abb Vie, please visit us at  Follow @abbvie on Linked In, Facebook, Instagram, Xand You Tube.

While the AI innovation race in Biopharma is focused on Drug discovery, Product Development/ CMC represents the next barrier/ bottleneck. The complexity of biological systems, the rigor of regulatory expectations, the pace of pipeline growth, and the enormous value at stake make this one of the highest-leverage domains for applied data science and AI in the entire pharmaceutical value chain.

We here at BTS - PDST, are building a dedicated, AI-native team that is driving cutting edge programs across early stage, late stage and commercial product development to accelerate E2E product development and launch, maximize yields of block buster products. Through our deep collaboration with PDST scientists we are boldly reimagining how Abb Vie can bring our pipeline products and lifesaving drugs to patients faster, safer and in cost effective manner fueled by AI.

Early-Stage Biologics Data Scientist is a senior individual contributor role built for a scientist-engineer who thinks in systems, builds with purpose, and leads through technical credibility. This role is a shaper of outcomes. You will embed AI and advanced analytics directly into Abb Vie's early-stage biologicspipelinesincluding process characterization studies, process robustness, and control strategy development. You will architect data solutions, build and deploy predictive models, and establish the analytical foundation that enables Abb Vie to make faster, smarter, more defensible decisions at every stage of commercial biologics development.

• Enterprise-scale scope:
  Enterprise-scale biologics portfolio spanning clinical, commercial, and lifecycle stages.
• Building AI playbook for the future:
  First-in-Abb Vie and first-in-biologics analytical approaches; you build the AI playbook for the future.
• Growth and Impact:
  Direct impact on regulatory submissions, commercial readiness, and manufacturing decisions through deep cross-functional exposure to manufacturing, quality, regulatory, and scientific leadership
• Mission:
  Every model you build helps ensure safe, reliable medicines reach patients at scale

Responsibilities:

Modeling & Predictive Analytics

• Develop, validate, and deploy predictive models that support process development decisions in early-stage biologics, including upstream bioprocess performance, downstream purification behavior, and critical quality attribute (CQA) outcomes.
• Design and apply hybrid modeling approaches — combining first-principles process understanding with data-driven techniques — to maximize predictive power while maintaining scientific interpretability.
• Build and evolve analytical frameworks that support digital twin concepts and in-silico process optimization, enabling smarter experimental strategies and accelerated development timelines.

Data Strategy & Architecture

• Partner with process scientists, analytical scientists, and engineers to define data strategies for new programs — including what data to collect, how to structure it, and how to connect it across experimental campaigns.
• Identify and address data quality, integration, and accessibility challenges that limit the value of existing datasets; advocate for and help implement improved data infrastructure within the pod.
• Ensure that models, analyses, and data assets are built in a manner consistent with GxP principles and regulatory expectations, with appropriate documentation and traceability.

Intelligent Workflow Design

• Function as a solution architect for analytical and AI-driven workflows: select the right approach for each problem — whether that means classical statistical methods, supervised or unsupervised machine learning,…