Associate Principal Scientist, Data Engineer, Digital Insights, DSCS Digital Technologies

Associate Principal Scientist, Data Engineer, Digital Insights, DSCS Digital Technologies

We are a global biopharmaceutical leader dedicated to developing and delivering innovative products that save and improve lives. We seek an Associate Principal Scientist to join our Digital Insights team within the Development Sciences and Clinical Supply (DSCS) Digital Technologies organization. The role will focus on designing, building and maintaining data pipelines that capture, curate and deliver experimental and process data from Sterile Product Development (SPD) teams to downstream digital initiatives including mechanistic and data‑driven process modeling and Bayesian optimization approaches.

• Build strong partnerships with SPD experimentalists, process engineers, and analytical scientists to gather requirements for data solutions.
• Design and implement robust, scalable data pipelines that ingest experimental and process data from SPD teams.
• Deliver analysis‑ready datasets to support SPD digital initiatives, including process modeling and Bayesian optimization.
• Define and enforce data standards, metadata schemas, and ontologies that make SPD data interoperable and readily consumable by downstream modeling and optimization workflows.
• Automate data ingestion from laboratory instruments, electronic lab notebooks, PAT systems, and manufacturing systems and integrate with cloud‑based storage and compute environments.
• Apply and generate data analysis and visualization workflows.
• Design and develop dashboards, reports, and data exports.
• Curate data and support definition of needs for automation of data ingestion.
• Influence digital data strategy for SPD by identifying opportunities to improve data capture practices at the source and reduce friction between experimentation and modeling.
• Demonstrate excellent interpersonal, communication, and collaboration skills.
• Embrace and model core values, fostering a supportive culture where all can thrive.
• Collaborate effectively in a dynamic, integrated, and multidisciplinary team environment.
• Perform impactful scientific innovation in a team‑oriented manner that builds trusted partnerships across vast stakeholder networks.
• Publish and present research, including maintaining an established track record of interaction with the broader academic community.

• Ph.D. in Computer Science, Data Science, Engineering, Chemistry, Physics, Biology, Pharmaceutical Sciences, or a closely‑related field with at least 3 years of industrial/pharmaceutical or relevant experience.
• M.S. in the same fields with at least 5 years of industrial/pharmaceutical or relevant experience.
• B.S. in the same fields with at least 7 years of industrial/pharmaceutical or relevant experience.

• Proficient in Python and/or another programming language (e.g., Java, R).
• Comfortable working in development environments such as Posit/RStudio/Jupyter.
• Solid SQL skills with hands‑on experience writing and optimizing queries against relational databases.
• Experience with ETL/ELT processes and building data pipelines in a scientific or pharmaceutical context.
• Familiarity with cloud platforms (AWS, Azure, or GCP) for data storage, processing, and integration.
• Prior hands‑on experience in sterile drug product development or related pharmaceutical development, with a demonstrated transition into a data engineering, data science, or computational role.
• Working knowledge of how mechanistic and data‑driven models consume and depend on experimental data, sufficient to anticipate modeler needs and deliver appropriately structured datasets.
• Ability to deliver complex solutions under compressed timelines in a dynamic environment.

• Experience with sterile CMC development workflows, particularly unit operations such as mixing, pooling, pumping, filling, filtration, or freeze‑drying.
• Familiarity with formulation optimization studies, Bayesian optimization, or related model‑guided experimental design approaches.
• Familiarity with mechanistic and/or data‑driven modeling approaches, not necessarily as a modeler, but understanding input/output data requirements and validation…