Join GSK as a Senior Chemometrics Engineer

GSK is a global biopharma company dedicated to uniting science, technology, and talent to get ahead of disease together. Our mission is to positively impact the health of 2.5 billion people over the next 10 years.

About the Role

The CMC Applied Data Science (CADS) group, part of Digital and Data (D&D), is responsible for data science, computational science, and modeling to support the technical process and product development of new vaccines and drug products at GSK. We analyze & model molecular structure data, high-dimensional biological datasets (bioinformatics and genomics), AI/ML applications in process/product development, chemometrics, and spectral data from various instruments, and model production processes.

The CMC Chemometrics Delivery team focuses on developing proof-of-concept to production-ready data science products that combine the latest advances in chemometrics (spectroscopy, chromatography, time series) with top industry software development standards.

Your Responsibilities

• Deliver end-to-end data science projects, including spectra, hyperspectral, and chromatograms processing, model building, and deployment in biological processes, high-dimensional data analysis, and Process Analytical Technology (PAT).
• Identify new opportunities for applying innovative data analytics approaches for our business partners by establishing productive relationships with stakeholders.
• Coach junior team members and help scientists upskill.
• Collaborate on innovative chemometrics/ML approaches to solve complex problems.
• Contribute to and co-author reports for regulatory authorities, scientific papers, congress reports, or other communication material for internal and external stakeholders.
• Communicate CADS activities, results, and principles to internal stakeholders, translating complex solutions into simple, clear, and effective messages.
• Represent CADS and D&D as a chemometrics or PAT subject matter expert in cross-functional project teams.
• Lead initiatives to drive continuous improvement of chemometrics projects' quality and efficiency, especially topics related to CI/CD.
• Work closely with our scientific software delivery team to turn scientific applications into well-designed and validated scientific applications used by stakeholders.

Why You?

Basic Qualifications:

• University degree (MSc) in Chemometrics, Machine Learning, or equivalent experience with a strong background in spectra data analysis, multivariate statistics, and analytical methods qualification.
• At least 5 years of experience in chemometrics and related fields.
• Experience in advanced chemometrics methods for process modeling (MSPC, MCR) and data wrangling for signal processing and feature extraction.
• Understanding of statistical aspects linked to ICH Q8, Quality by Design (QbD), and Process Analytical Technology (PAT) principles.
• Experience with bioassays and analytical techniques such as Infrared, Near Infrared, Raman, Fluorescence 3D, Hyperspectral Camera, Capacitance, HPLC, LC-MS, Electrophoresis.
• Familiarity with standard industry software such as SIPAT or Process Pulse platforms.
• Strong programming and data analytics skills in Python and/or MATLAB. Familiarity with software development support tools (e.g., Azure DevOps).
• Good communication skills, ability to simplify complex problems, and communicate complex solutions effectively.
• Experience mentoring junior data scientists.
• Fluent in English.

Preferred Qualifications:

• PhD in Chemometrics, Machine Learning, or equivalent experience with a strong background in 3D spectra data analysis, multivariate statistics, Design of Experiments, process optimization, and analytical methods qualification.
• Good networking skills and fluent interactions with one or more scientific communities.
• Good leadership skills in a scientifically oriented environment.
• Understanding of the pharmaceutical industry business.
• Knowledge of deep learning and predictive modeling, including CNNs, RNNs, time-series analysis, and general techniques such as SVM, random forest.
• Experience with biological process development and SIMCA/SIMCA Online.
• Fluency in French or Italian is a plus.

If you have a disability and require