Job responsibilities
Decompose the document corpus to an “atomic” level (clauses, obligations, controls, defined terms, and cross-references) and convert it into structured data
Apply text analytics methods (e.g., entity and relationship extraction, similarity, clustering, and topic modelling) to map how documents connect and inform data-product structures
Profile the governed data estate for completeness, duplication, drift, orphaned references, and structural anomalies, and report findings that inform design and remediation priorities
Support knowledge-graph representations that make cross-document relationships queryable for retrieval, impact analysis, and AI grounding
Prototype and iterate conceptual, logical, and physical data models (entities, attributes, cardinality, hierarchy, and lineage) and validate them against real content at scale
Build and maintain reference data for canonical taxonomies, including mappings from source content to canonical forms
Partner with Technology on implementation details (data contracts, schema binding, transformation logic, and validation rules) and support testing for new or amended data products
Design and run analyses and experiments using Python and SQL to answer data-product and governance questions (e.g., overlap analysis, citation graphs, and term drift) and explain results clearly to non-specialists
Support evaluation of retrieval and extraction quality, including labelling, gold-set curation, and error analysis for AI-generated structured output
Produce analytical artefacts for governance decisions (e.g., profile reports, coverage analysis, similarity mapping, and change impact assessments) with a clear audit trail from source content to conclusion
Help refine the data-products backlog by breaking down requests into work items, estimating effort, and sequencing delivery with partners
Required qualifications, capabilities and skills
Experience in a hands-on data analyst, data scientist, or data modeler role, including entity/relationship modelling, data profiling, and analysis on real business content
Working knowledge of Python and SQL for data analysis, including pandas and notebook-based workflows, and one or more of: scikit-learn, spaCy (or another NLP library), or graph libraries
Experience applying data-science techniques (statistical analysis, similarity, clustering, entity/relationship extraction, topic modelling) to unstructured or semi-structured text content
Familiarity with conceptual, logical, and physical data modelling, including normalization, canonical modelling, cardinality, and lineage
Ability to partner across Technology, Data Science, Product, and business subject matter experts across regions, balancing rigor on definitions with pragmatic delivery
Familiarity with generative AI tools used for analysis and development, and understanding how governed structured data underpins safe AI consumption
Preferred qualifications, capabilities and skills (max 7 bullets)
Experience analysing or modelling policy, regulatory, or control-related content (e.g., obligations, controls, standards, procedures)
Working knowledge of knowledge graphs and graph analytics, including ontology/taxonomy design for entity relationships, citation networks, and controlled vocabularies
Familiarity with modern data catalog, lineage, and data modelling tools
Exposure to extraction and evaluation techniques for structured output, including gold-set curation and error analysis
Familiarity with JPMorganChase data standards and firmwide governance operating models
Experience with common delivery and reporting tools (e.g., Jira, Confluence, and dashboard tools)
Experience operating in a controlled environment with governance processes, audit interactions, and documentation rigor