Context Engineer-II

Working with Us Challenging. Meaningful. Life-changing. Those aren’t words that are usually associated with a job. But working at Bristol Myers Squibb is anything but usual. Here, uniquely interesting work happens every day, in every department. From optimizing a production line to the latest breakthroughs in cell therapy, this is work that transforms the lives of patients, and the careers of those who do it. You’ll get the chance to grow and thrive through opportunities uncommon in scale and scope, alongside high-achieving teams. Take your career farther than you thought possible. Bristol Myers Squibb recognizes the importance of balance and flexibility in our work environment. We offer a wide variety of competitive benefits, services and programs that provide our employees with the resources to pursue their goals, both at work and in their personal lives. Read more: careers.bms.com/working-with-us . Position Summary The Context Engineer is responsible for supporting the design, implementation, maintenance, and governance of the enterprise semantic layer that underpins the organization’s Commercial data strategy. Working with and functionally reporting to the Lead Data Architect, this role helps develop and operationalize ontological models, taxonomy frameworks, business glossaries, metadata management practices, business context layers, and semantic governance processes that enable consistent interpretation of Commercial data across Sales, Marketing, Market Access, Medical Affairs, Regulatory Affairs, Finance, Analytics, and data product teams. Key Responsibilities Support the Lead Data Architect in designing, implementing, maintaining, and governing the enterprise semantic layer that underpins the Commercial data strategy and enables consistent interpretation of data across Sales, Marketing, Market Access, Medical Affairs, Regulatory Affairs, Finance, Analytics, and data product teams. Develop and maintain ontological models that represent Commercial domain knowledge structures, including products, stakeholders, channels, outcomes, metrics, business events, and their interrelationships, enabling consistent reasoning across systems, analytical platforms, data products, and AI-enabled solutions. Design and maintain taxonomy frameworks and classification structures for Commercial content, data assets, business processes, domains, entities, and use cases, enabling reliable search, segmentation, reporting, reuse, and alignment with pharma commercial operations. Build, maintain, and govern the Commercial business glossary, ensuring critical business terms, commercial KPIs, data definitions, business rules, calculations, and regulatory concepts are clearly defined, consistently used, and aligned with approved business meaning. Establish and apply metadata management practices for Commercial data assets, including ownership, stewardship, source system, refresh frequency, sensitivity classification, lineage, quality expectations, access considerations, and usage restrictions. Design, implement, and maintain the business context layer that translates technical Commercial data structures into business-ready, context-enriched representations for self-service analytics, consistent reporting, data product delivery, reusable AI context, and AI-ready consumption across the Commercial organization. Maintain semantic mappings between business concepts, glossary terms, data models, source systems, data products, reports, and AI context assets to improve traceability, discoverability, reuse, and impact analysis across the Commercial data ecosystem. Operate semantic governance processes for ontologies, taxonomies, glossaries, metadata standards, context assets, and semantic mappings, ensuring changes are reviewed, documented, versioned, auditable, and aligned with enterprise data governance expectations. Partner with data architects, data engineers, product owners, analysts, governance teams, privacy/compliance partners, and business stakeholders to validate definitions, resolve semantic ambiguity, and ensure context assets reflect approved Commercial business meaning. Support compliance-aware documentation and governance practices by ensuring semantic assets reflect applicable privacy, data use, auditability, access control, and pharma regulatory considerations in a regulated life sciences environment. Preferred Skills & Certifications AI context engineering experience, including reusable context assets, prompt/context packages, AI-ready documentation, retrieval-augmented generation concepts, and knowledge graph-enabled retrieval. Semantic modeling and knowledge representation skills, including ontologies, taxonomies, semantic mappings, controlled vocabularies, business glossaries, and metadata standards. Familiarity with semantic technologies and tools such as RDF/RDFS, OWL, SPARQL, SKOS, SHACL, JSON-LD, Protégé, PoolParty, TopBraid, or equivalent platforms. Experience with data catalog, metadata, governance, and lineage platforms such as Collibra, Alation, Atlan, Microsoft Purview, Informatica Axon, or equivalent tools. Working knowledge of data architecture and engineering concepts, including data models, data products, data contracts, lineage, SQL, Python, dbt, Snowflake, Databricks, Redshift, or similar cloud data platforms. Familiarity with Commercial pharma data ecosystems, including Veeva, IQVIA, Symphony Health, APLD, HCP/HCO master data, payer/market access data, claims, or patient services data. Understanding of responsible AI, privacy, access control, data use restrictions, auditability, and regulated life sciences data governance practices. Preferred certifications may include DAMA CDMP, Collibra, Alation, Microsoft Azure Data or AI, Databricks, Snowflake, Informatica, or equivalent data governance, data engineering, or AI-related credentials. Qualifications Bachelor’s degree required in Computer Science, Information Science, Life Sciences, Data Science, In