Remote Data Engineer: Graphs, Neo4j & AI Retrieval

Darwoft; United States; Remote; USD 90,000 - 130,000; Full time

Benefits offered by this job

Fully remote

Argentina time alignment (UTC-3)

Job summary

Darwoft is seeking a semi-senior knowledge graph engineer to build and evolve a graph-based knowledge base spanning legal and regulatory domains. You will translate conceptual models into production graph structures, collaborating with data science, backend, and AI teams to support retrieval-augmented workflows.

You will implement data pipelines using Neo4j and Cypher, ensure scalable, maintainable solutions, and contribute to semantic search capabilities across large datasets.

Qualifications

• Three to five years of experience at a semi-senior level.
• Practical experience with Neo4j, Cypher, and graph data modeling.
• A solid foundation in data engineering and building production-ready systems.
• Ability to translate conceptual data models into effective graph structures.
• Interest in knowledge graphs and their use in AI-powered information retrieval.

Responsibilities

• Model and maintain graph data structures for large volumes of domain information.
• Develop data engineering solutions using Neo4j and Cypher.
• Connect concepts and entities to support semantic exploration and intelligent search.
• Turn taxonomies, ontologies, and conceptual models into efficient graph representations.
• Work with data science, backend, and AI teams to feed graph data into retrieval architectures.
• Build solutions with attention to scalability, maintainability, and production use.

Skills

Neo4j

Cypher

Graph data modeling

Data engineering

Knowledge graphs

AI-powered retrieval

Job description

Darwoft is seeking a semi-senior knowledge graph engineer to build and evolve a graph-based knowledge base spanning legal and regulatory domains. You will translate conceptual models into production graph structures, collaborating with data science, backend, and AI teams to support retrieval-augmented workflows.

You will implement data pipelines using Neo4j and Cypher, ensure scalable, maintainable solutions, and contribute to semantic search capabilities across large datasets.