Principal Research Scientist I, Biologics CMC Developability Modeling

North Chicago, IL, United Statesfull time

Apply on Employer Site

On Site

senior

H1B: yes

AbbVie Principal Research Scientist I at AbbVie leading modeling efforts within the Biologics CMC Developability Team. The role involves serving as a technical expert, collaborating across teams, performing laboratory experiments, and integrating scientific trends into development strategies.

Responsibilities

Serve as a technical expert for modeling within Biologics CMC Developability Team
Represent BCD in modeling communities within AbbVie; collaborates with other modelers or teams to ensure business needs are met by the correct modeling framework
May perform in vitro laboratory experiments; works closely with teams for design of wet lab studies to build both models and fundamental knowledge of protein solution behavior
Identifies emerging scientific and technological trends from multiple internal and external sources, assesses relevance and integrates applicable trends into BCD plans and strategies as appropriate. Present data at internal and external professional conferences and prepare manuscripts for publication in peer reviewed journals or patent applications
May serve as BCD Lead, coordinate developability assessment activities for 1-2 Discovery Projects at a time
Experience with cross-functional decision making across reporting lines
BS, MS, or PhD in Pharmaceutics, Pharmaceutical Sciences, Chemistry, Chemical Engineering, or related disciplines with 14+ (Bachelors), 12+ (Masters), or 6+ (PhD) years of relevant industry experience.
Proven ability to solve critical scientific problems.
Direct experience with applying modeling techniques (mechanistic or statistical) to protein long-term stability or formulation screening such as kinetic degradation modeling
Well versed in predictive machine learning and statistical modeling techniques
Familiar with complex ML architectures including deep learning and hierarchical or multi-task frameworks
Skilled with feature attribution, sensitivity analysis, and model interpretability