Data and Knowledge Engineer
Description
Role: Data and Knowledge Engineer
Location: New York
Work Model: Hybrid, 3 days a week onsite at Morgan Stanley office
Employment Type: Contractual
Description
We are looking for a Data and Knowledge Engineer to build the pipelines and knowledge graphs behind enterprise semantic and AI platforms. You will move data from Snowflake and other sources into graph databases such as Stardog and GraphDB, using ELT/ETL, Python and R2RML mappings. The work supports agentic AI use cases built on ontologies.
Key Responsibilities
• Build and maintain scalable data pipelines (ELT/ETL) in Python and Snowflake.
• Ingest and change data from varied sources into knowledge graphs on Stardog and/or GraphDB.
• Write R2RML mappings to turn relational data into RDF according to enterprise ontologies.
• Write and tune SPARQL queries for data access, validation and downstream applications.
• Work with semantic architects to implement ontologies and knowledge models in production.
• Connect knowledge graphs to agentic AI and LLM workflows for retrieval, grounding and reasoning.
• Ensure data quality, monitoring, documentation and CI/CD for data and graph pipelines.
Primary Skills (Must Have)
• Python
• Snowflake
• ELT / ETL
• Data Pipelines
• Stardog
• GraphDB
• SPARQL
• R2RML
Desired Skills (Good to Have)
• Combining Agentic AI with Ontologies
• RDF / OWL modelling
• Orchestration tools (Airflow, dbt, etc.)
Skills
Sign in to read and join the discussion.