Scientific Technical Lead, Late Stage CMC
AbbVie
August 14, 2026
Remote friendly (North Chicago, IL)
United States
$109,500 - $208,500 USD yearly
Operations
Responsibilities
- Design, build, and deploy predictive and prescriptive models for process robustness assessment, control strategy optimization, and commercial process validation across late-stage biologics programs.
- Develop multivariate and time-series modeling to identify critical process parameter interactions, predict process drift, and support proactive deviation prevention at commercial sites.
- Apply advanced statistical/ML methods (dimensionality reduction, anomaly detection, Bayesian inference, hybrid mechanistic-empirical models) to characterize bioprocess behavior and define process design spaces.
- Build and maintain “golden batch” frameworks and optimization models as living benchmarks for process performance across sites and over time.
- Lead development of data infrastructure and analytical tools to enable intelligent, data-driven technology transfer from development to commercial manufacturing.
- Build cross-site process intelligence systems to compare/contextualize process data across distributed sites and equipment trains.
- Partner with manufacturing science and quality to define data requirements, standards, and analytical continuity.
- Architect AI/analytics solutions (classical stats, ML, retrieval-augmented systems, orchestrated agents, hybrid mechanisms) and establish modeling/validation/deployment standards for GxP.
- Define and drive data strategy (acquisition planning, ontology, quality standards; integration across LIMS, MES, historian, eBR).
- Ensure data/model documentation, version control, and regulatory-consistent standards (e.g., 21 CFR Part 11; ICH Q8/Q9/Q10).
- Translate analytics into actionable narratives for manufacturing, quality, regulatory, and executive audiences; influence decisions without formal authority; mentor junior team members.
Qualifications
Required:
- BS in CS/related + 7 years IT/application development; or MS + 6 years; or PhD + 2 years.
- Hands-on experience building/deploying data science/ML solutions in scientific/engineering environments.
- Expert Python; NumPy, pandas, scikit-learn, PyTorch/TensorFlow; modern data engineering (cloud/big data/pipeline orchestration).
- Business analytics foundation (R, Dataiku, AWS SageMaker, Spark, Tableau).
- Strong statistical modeling/experimental design/multivariate analysis/uncertainty quantification.
- Familiarity with knowledge graphs and retrieval-augmented/orchestrated AI/LLM systems.
- Experience in GxP-regulated environments; working knowledge of FDA/EMA process validation, CPV, and control strategy.
- MLOps/model lifecycle management in regulated/enterprise settings.
- Ownership, solution-architect mindset, scientific integrity, credibility/influence, bias for impact.
Preferred:
- MS/PhD in Data Science/Biostatistics/Engineering/Computational Biology or related.
- 5+ years relevant ML/data science experience.
- Biologics manufacturing/late-stage process development/commercial bioprocess operations (upstream and/or downstream).
- Stability analytics, comparability assessments, and post-approval change management.
- Experience with LIMS/MES/DeltaV/historian/eBR data and scalable data pipelines.
- Track record of scientific communication (publications/regulatory submissions/technical reports).
- Familiarity with technology transfer workflows, process characterization study design, and PPQ/PV.
Benefits
- Paid time off, medical/dental/vision insurance, and 401(k) (eligible employees).
- Eligible to participate in long-term incentive programs.
Application instructions
- Not specified.
- Design, build, and deploy predictive and prescriptive models for process robustness assessment, control strategy optimization, and commercial process validation across late-stage biologics programs.
- Develop multivariate and time-series modeling to identify critical process parameter interactions, predict process drift, and support proactive deviation prevention at commercial sites.
- Apply advanced statistical/ML methods (dimensionality reduction, anomaly detection, Bayesian inference, hybrid mechanistic-empirical models) to characterize bioprocess behavior and define process design spaces.
- Build and maintain “golden batch” frameworks and optimization models as living benchmarks for process performance across sites and over time.
- Lead development of data infrastructure and analytical tools to enable intelligent, data-driven technology transfer from development to commercial manufacturing.
- Build cross-site process intelligence systems to compare/contextualize process data across distributed sites and equipment trains.
- Partner with manufacturing science and quality to define data requirements, standards, and analytical continuity.
- Architect AI/analytics solutions (classical stats, ML, retrieval-augmented systems, orchestrated agents, hybrid mechanisms) and establish modeling/validation/deployment standards for GxP.
- Define and drive data strategy (acquisition planning, ontology, quality standards; integration across LIMS, MES, historian, eBR).
- Ensure data/model documentation, version control, and regulatory-consistent standards (e.g., 21 CFR Part 11; ICH Q8/Q9/Q10).
- Translate analytics into actionable narratives for manufacturing, quality, regulatory, and executive audiences; influence decisions without formal authority; mentor junior team members.
Qualifications
Required:
- BS in CS/related + 7 years IT/application development; or MS + 6 years; or PhD + 2 years.
- Hands-on experience building/deploying data science/ML solutions in scientific/engineering environments.
- Expert Python; NumPy, pandas, scikit-learn, PyTorch/TensorFlow; modern data engineering (cloud/big data/pipeline orchestration).
- Business analytics foundation (R, Dataiku, AWS SageMaker, Spark, Tableau).
- Strong statistical modeling/experimental design/multivariate analysis/uncertainty quantification.
- Familiarity with knowledge graphs and retrieval-augmented/orchestrated AI/LLM systems.
- Experience in GxP-regulated environments; working knowledge of FDA/EMA process validation, CPV, and control strategy.
- MLOps/model lifecycle management in regulated/enterprise settings.
- Ownership, solution-architect mindset, scientific integrity, credibility/influence, bias for impact.
Preferred:
- MS/PhD in Data Science/Biostatistics/Engineering/Computational Biology or related.
- 5+ years relevant ML/data science experience.
- Biologics manufacturing/late-stage process development/commercial bioprocess operations (upstream and/or downstream).
- Stability analytics, comparability assessments, and post-approval change management.
- Experience with LIMS/MES/DeltaV/historian/eBR data and scalable data pipelines.
- Track record of scientific communication (publications/regulatory submissions/technical reports).
- Familiarity with technology transfer workflows, process characterization study design, and PPQ/PV.
Benefits
- Paid time off, medical/dental/vision insurance, and 401(k) (eligible employees).
- Eligible to participate in long-term incentive programs.
Application instructions
- Not specified.