Senior Specialist, Data Science

Job description

Job Description About the OrganizationThe Biologics Science and Technology Platforms, Data, Modeling, and Statistics (PDSM) organization is a highly technical, science-forward function embedded within Bio S&T. We partner closely with manufacturing sites, IT, and process engineers to deliver data-driven process insights, statistical modeling, and digital capabilities that accelerate biologics commercialization and manufacturing excellence. Our mission is to bridge the gap between traditional process engineering and modern data science. We build the foundational architectures, digital workflows, and analytical models that underpin every initiative across the biologics network—enabling proactive process monitoring (PPM), continued process verification (CPV), yield optimization, tech transfer, and AI-ready manufacturing. We work hand-in-hand with our IT and manufacturing partners to co-design process analytics platforms. Our team contributes deep bioprocessing domain understanding paired with technical data science capabilities, ensuring the right process parameters and quality attributes are captured, contextualized, and modeled to drive real operational outcomes. Position SummaryThe Senior Specialist, Advanced Process Analytics & Data Strategy is a technical individual contributor role within PDSM. The primary expectation is hands-on execution and support, applying data science, process modeling, and data architecture concepts to strengthen biologics manufacturing analytics. The successful candidate will use their bioprocess engineering background to develop, maintain, and improve analytics solutions, support process standardization, and collaborate closely with scientists, engineers, and digital teams. We are seeking candidates who fit the Domain-to-Data Professional profile: A bioprocess, biochemical, or regulated manufacturing engineer who has developed meaningful data science expertise through hands-on work with process, analytical, and batch data. You must be able to apply tools such as Python, R, SQL, and statistical modeling to support process characterization, digital analytics, root-cause investigations, and regulatory-ready manufacturing data products. Key Responsibilities1. Biologics Process Analytics & Engineering SupportSupport the development and execution of process analytics activities that connect unit operations, process parameters, and quality attributes through structured manufacturing data models. Translate bioprocessing and manufacturing needs into clear data requirements and help convert available data capabilities into practical scientific and operational insights. Contribute to process-focused data initiatives by performing analysis, developing datasets and visualizations, documenting requirements, and coordinating with engineers, scientists, and IT partners. 2. Manufacturing Data Architecture & ContextualizationBuild and maintain a clear data flow map across the biologics manufacturing network, integrating core manufacturing systems (MES, LIMS, PI Historian, SAP, ELN). Support process data contextualization and ontology mapping by helping link raw process and analytical data across unit operations, sites, and product lifecycle stages. Collaborate with IT and data engineering partners to support scalable, GxP-compliant data solutions by providing bioprocess domain context, data validation, and user requirements. Support data integrity expectations by applying ALCOA+ principles during data review, validation, documentation, and routine use of manufacturing data products. 3. Process Monitoring, Modeling & Statistical EnablementDevelop and deploy fit-for-purpose dashboards, process visualizations, and analytics to enable Proactive Process Monitoring (PPM), trend identification, and rapid root-cause investigation support.Work with Statistical Sciences and Process/Product Modeling teams to prepare, structure, and validate datasets that support CPV, digital twins, AI/ML models, and multivariate analysis. Collaborate with internal manufacturing sites and Contract Manufacturing Organizations (CMOs) to establish sustainable data access and improve the usability of process/analytical data for technical troubleshooting. 4. Process Governance & Standardization SupportApply established process data standards, nomenclature, and ownership models to support cross-site comparability and reliable reuse of manufacturing data. Participate in data stewardship activities by maintaining documentation, identifying data quality issues, and supporting routine governance practices with engineering and science teams. 5. Stakeholder Engagement & Capability BuildingCollaborate with Technical Product Managers, process SMEs, Quality, Regulatory Affairs, and IT to support shared process-analytics priorities and deliverables. Support digital and data literacy across Bio S&T by preparing templates, job aids, training materials, and examples that help users apply governed self-service analytics appropriately. Education RequirementsB.S. in Chemical Engineering, Biochemical Engineering, Bioengineering, Life Sciences, or a related field with 5+ years of relevant biopharmaceutical experience. M.S. in the same fields with 3+ years of relevant experience, or Ph.D. with 1+ years of relevant experience. Required Experience and SkillsBioprocess Engineering & Domain ExpertiseStrong foundational knowledge of biologics manufacturing (Upstream/Downstream Proven experience utilizing process data (PI Historian, MES, LIMS) to troubleshoot manufacturing issues, monitor process performance, or support regulatory filings. Deep understanding of GMP/GxP environments, Continued Process Verification (CPV), and quality/compliance requirements in biomanufacturing. Data Science & Technical EngineeringHands-on experience with Python or R for data manipulation, statistical analysis, and scripting—applied specifically to scientific or manufacturing datasets. Moderate to strong hands-on SQL skills; ability to query, transform, and validate data across relational databases. Understanding of how to extract and structure time-series data (e.g., from PI/DeltaV) and relational batch data to build actionable process models. Familiarity with data architecture concepts (data lakes, data warehousing) and experience collaborating with IT/Data Engineering to operationalize analytical pipelines. Collaboration, Execution, and CommunicationStrong execution skills with the ability to translate defined priorities into clear workplans, analyses, documentation, and deliverables. Ability to work effectively across technical, business, Digital, Quality, and external partner stakeholders to gather input, resolve issues, and support aligned execution. Ability to support adoption of new data practices and tools by preparing clear instructions, examples, and user-facing support materials. Ability to translate complex technical and data concepts into clear, actionable recommendations for both technical and non-technical audiences. Comfortable working in evolving technical areas with guidance from functional leads and SMEs, including clarifying requirements and identifying practical next steps. Demonstrated ability to contribute as a reliable technical team member by sharing knowledge, documenting methods, and supporting peers through hands-on problem solving. Preferred Experience and SkillsExperience with biologics manufacturing data systems and the specific data challenges associated with bioprocess scale-up, tech transfer, and commercial manufacturing. Familiarity with data platform and mapping standards, OSIsoft PI / PI AF, Seeq, Power BI, Spotfire, Dataiku, JMP, AWS, Databricks. Experience preparing technical documentation, data dictionaries, mapping files, user requirements, or validation summaries for manufacturing data workflows. Background in PPM, CPV, investigation support analytics, cross-site process robustness analysis, or statistical process control in a GMP environment. Experience with extern