Data Analytics Support for MVDA Study

Data Analytics Support for MVDA Study

Scope:

The engagement will require the following:

• Drive activities to schedules and milestones
• Use SIMCA and Python tools to perform MultiVariate Data Analysis (MVDA)
• Exploring process trends and variability.
• Work with large datasets from bioprocessing systems—cleaning, organizing, and preparing them for analysis.
• Apply techniques like PCA, PLS, clustering, and tree-based machine learning models to uncover insights.
• Collaborate with internal teams to understand data handling & analysis needs, and help interpret results.
• Summarize findings with clear messages and contribute to presentations for stakeholders.

Requirements:

The engagement will require the following skills:

• Drive activities to schedules and milestones
• Solid experience with SIMCA for MVDA work.
• Strong Python skills, especially with data handling libraries like Pandas.
• Good understanding of bioprocessing—both upstream and downstream operations and control strategies.
• Familiarity with MVDA methods like PCA and PLS and working with latent variable models.
• Exposure to interpretable machine learning (IML) techniques and predictive modeling is a plus.

Preferred Qualifications

• Experience troubleshooting bioprocess issues such as product quality attribute shifts, process performance variability, or yield inconsistencies.
• Knowledge of biopharmaceutical data analysis and approaches to assess process robustness.
• Comfortable communicating across technical and non-technical teams.