Metadata Architect: Knowledge Catalog & AI Grounding

Capgemini; New Jersey; On-site; USD 32,000 - 50,000; Full time

Benefits offered by this job

Medical benefits

Dental benefits

Vision benefits

Retirement benefits

Job summary

Tundra Technical Solutions is seeking a metadata-focused data professional to design, enrich, and automate enterprise metadata catalogs across cloud data stores and AI platforms. You will partner with data teams to define governance, ownership, and taxonomy guidelines, ensuring data assets remain discoverable and trustworthy.

Responsibilities include building catalog structures, automating ingestion, and enabling AI grounding with curated metadata.

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.

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.

Skills

SQL

Python

Metadata management concepts

Data governance & compliance

APIs & automation tooling

Tools

Dataplex APIs

Cloud Functions

Dataform

Vertex AI

Gemini Ent. AI / Vertex AI

Job description

Tundra Technical Solutions is seeking a metadata-focused data professional to design, enrich, and automate enterprise metadata catalogs across cloud data stores and AI platforms. You will partner with data teams to define governance, ownership, and taxonomy guidelines, ensuring data assets remain discoverable and trustworthy.

Responsibilities include building catalog structures, automating ingestion, and enabling AI grounding with curated metadata.