Graph Engineer

About the role Tenarai places small, senior engineering teams inside large enterprises and builds alongside the client's own people. This role is for a current engagement: a program at a major financial-technology company to build a governed knowledge graph and an AI-agent data platform — a single, trusted source of business meaning that the company's AI agents and analytics read from.

A knowledge graph is a store of business entities — customers, invoices, accounts — together with how they relate, so an AI agent can follow context rather than look up isolated facts. As a Knowledge Graph Engineer you design that graph, build the pipelines that fill it, keep it correct and versioned, and build the retrieval that lets agents and applications query across it.

What you'll do Design the schema and relationships of the graph with the client's domain experts, and model core business entities so each one has a single agreed definition.

Build and run the pipelines that ingest data into the graph, validate it, and version it, and stand up a staging environment that checks changes before they are published.

Build retrieval over the graph, including following links between entities and querying across more than one store, so a single query can answer across domains.

Model each business unit's own version of the core entities on top of the shared core, without changing the core itself.

Operate the graph once it is live: monitor it, keep it performant, and make it easy to inspect and visualize.

Work with the platform and forward-deployed engineers so the graph serves real use cases, not just a clean model.

What you'll bring Hands-on experience building with graph databases, whether property-graph or RDF stores such as Neo4j, Amazon Neptune, or TigerGraph.

Fluency in at least one graph query language, such as Cypher, SPARQL, or Gremlin.

Experience modelling data: ontologies, canonical or semantic models, and the discipline of one definition per concept.

Solid data-engineering skills for building ingestion and validation pipelines, and fluency in Python or a similar language.

An eye for correctness — validating a graph and the data in it, not just loading it.

Helpful, not required Retrieval for AI agents, including graph-based retrieval and hybrid approaches that combine a graph with vector search.

Agent tool protocols such as MCP, or serving a graph behind an API for applications.

Work in a financial, accounting, or other regulated domain.

Experience with change-data capture and keeping a graph in sync with upstream systems.

How we'll measure success Within two quarters, a versioned graph you built is the source several agents read from, retrieval over it answers real questions accurately enough to pass the agreed gates, and the core entities you modelled are in use across more than one team.

How we work You work with the client's domain experts and Tenarai's platform and forward-deployed engineers, and the graph is judged by whether real use cases answer correctly on top of it. We keep teams small, review each other's work, and prefer a graph that serves one or two use cases well over a model that serves none.

Tenarai is an equal-opportunity employer. To apply, send a short note and an example of graph or data-modelling work you have shipped to careers@tenarai.example. Replace this address with the live one before posting.