Role Name: Knowledge Context Engineer
Work site: Bernards Township NJ (onsite)
Start date: Immediate availability.
Background check MANDATORY
Request ID: GSTV5H
Key Responsibilities:
· Design, configure, and maintain catalog structures (entries, aspect types, tags, glossaries) to organize data across BigQuery, Cloud Storage, Spanner, Vertex AI, Pub/Sub, and third-party sources.
· Curate and enrich metadata — business definitions, ownership, sensitivity classifications, lineage, and usage context — so data assets are discoverable and trustworthy.
· Build and maintain semantic layers, taxonomies, and ontologies that support natural-language search and AI grounding use cases.
· Automate metadata ingestion and tagging pipelines (e.g., via Dataplex APIs, Cloud Functions, or Dataform) to keep the catalog continuously up to date.
· Partner with data engineering, data governance, and business stakeholders to define and enforce cataloging standards, naming conventions, and data classification policies.
· Support data quality and profiling initiatives, publishing scan results as catalog metadata.
· Monitor catalog health, resolve metadata gaps or inconsistencies, and drive adoption across data and AI teams.
· Contribute catalog context to downstream AI/agentic use cases (e.g., enabling Gemini or MCP-based agents to query curated metadata).
· Document processes and provide training/enablement to data stewards and business users on catalog usage.
Required Qualifications:
· 3+ years of experience in data engineering, data governance, or metadata management.
· Strong SQL skills; working knowledge of Python for automation/scripting.
· Familiarity with metadata management concepts: lineage, data classification, business glossaries, taxonomy/ontology design.
· Understanding of data governance and compliance principles (access controls, sensitive data handling).
· Experience with APIs and automation tooling for metadata ingestion.
· Preferred Qualifications
· Experience with Gemini Ent. AI /Vertex AI, RAG architectures, or grounding AI agents in curated enterprise metadata.
· Familiarity with Dataform, Cloud Composer/Airflow, or similar orchestration tools.
· Exposure to data mesh or federated governance models.
· Prior consulting or client-facing experience.
· Soft Skills
· Strong attention to detail and a structured, systematic approach to organizing information.
· Ability to translate technical metadata into business-friendly context.
· Collaborative mindset — comfortable working across data engineering, governance, and business teams.
· Clear written and verbal communication for documentation and stakeholder enablement.
· Ingest metadata from knowledge sources
· Curation of Knowledge Assets – Business glossaries, tagging, aspect definition
· Build workflows to review and approve knowledge assets with key stakeholders
Identify knowledge gaps and mitigation
