AI/ML Data Knowledge Graph Engineer at Sapience AI in Seattle, WA or US Remote

Job description

• Where this role sits
• This role builds the structured knowledge that collective intelligence reasons over. You own the KO (knowledge object) graph: the layer that turns a community’s scattered expertise into connected, queryable knowledge the COGENT architecture can use.
• You work where messy real-world data becomes trustworthy structure: ingesting, resolving, connecting, and modeling knowledge so reasoning has something solid to stand on.
• You partner closely with neuro-symbolic AI and applied AI, and you are the reason the platform can answer questions that span a community’s knowledge instead of isolated documents.
• Why this role exists
• Language models are fluent, but fluency is not knowledge. To reason over a community’s expertise with rigor, the platform needs that expertise structured, connected, and trustworthy, not just retrieved as text.
• Building a knowledge graph from real, fragmented sources is hard: entities to resolve, relationships to infer, quality to enforce, and provenance to preserve. The graph is only as good as the engineering behind it.
• The AI/ML Data and KO Graph Engineer builds that foundation. You turn scattered knowledge into a graph the COGENT architecture can reason over, so members get answers grounded in their community’s real expertise.
• What success looks like
• Connected knowledge. A community’s scattered expertise becomes a connected, queryable graph.
• Trustworthy answers. Quality and provenance let members trust and trace what the platform tells them.
• Fresh and current. The graph keeps pace with a community’s changing knowledge.
• Reasoning-ready. The graph serves both symbolic reasoning and neural retrieval well.
• Reusable ingestion. New sources come online faster because ingestion is reusable.
• Measured quality. Coverage, quality, and freshness are measured and improving.

Responsibilities

• You hold seven areas of responsibility across the knowledge layer. Each one is yours to set direction on, build, and measure.
• Build and maintain the KO graph that structures a community’s knowledge for reasoning.
• Design schemas, ontologies, and relationships that reflect how expertise actually connects.
• Make the graph queryable, performant, and reliable at scale.
• Build pipelines that extract knowledge from documents, systems, and community sources into the graph.
• Turn unstructured and semi-structured content into structured knowledge objects.
• Keep the graph current as a community’s knowledge changes.
• Resolve entities, deduplicate, and connect knowledge across fragmented sources.
• Enforce quality so members can trust what the graph tells them.
• Detect and handle conflicts and gaps in the knowledge.
• Preserve provenance so every piece of knowledge can be traced to its source.
• Build the structure that lets the platform show its work and earn member trust.
• Protect sensitive community knowledge with correct access and governance.
• Partner with neuro-symbolic and applied AI to serve the graph into reasoning and retrieval.
• Shape the graph so it supports both symbolic reasoning and neural retrieval.
• Make knowledge access fast enough for production answers.
• Build the data pipelines and platform the knowledge layer depends on.
• Instrument the pipelines so quality and freshness can be measured.
• Turn recurring ingestion needs into reusable connectors.
• Measure the quality, coverage, and freshness of the graph against what communities need.
• Build the evaluation that tells whether the knowledge layer is improving.
• Use evidence to steer where to invest next.

Requirements

• Required qualifications
• Five or more years in data engineering, knowledge graph engineering, or a related field.
• Hands-on experience building and operating knowledge graphs or graph databases.
• Strong data pipeline engineering, including ingestion and transformation.
• Experience with entity resolution, deduplication, and data quality.
• Solid grounding in knowledge representation, ontologies, or schema design.
• Strong Python and SQL, plus graph query languages.
• Care for provenance, trust, and protection of sensitive data.
• Knowledge graph and ontology engineering.
• Ingestion, extraction, and transformation pipelines.
• Entity resolution, deduplication, and data quality.
• Provenance, governance, and protection of sensitive knowledge.
• Serving graphs into retrieval and reasoning.
• Evaluation of knowledge quality and coverage.
• Turning recurring ingestion into reusable capability.
• Graph databases (for example Neo4j-class systems) and graph query languages (Cypher, SPARQL, or GQL).
• Data pipeline and orchestration tools.
• Entity resolution and data-quality tooling.
• Vector databases and embedding models for hybrid retrieval.
• Python and SQL as primary languages.
• Cloud data platforms and storage.
• Building and serving the KO graph into the COGENT architecture and MINERVA.
• Prior data or knowledge graph engineering at a software or AI company.
• Experience building knowledge structures from messy, real-world sources.
• A track record of production data systems with quality and provenance.
• Experience supporting reasoning or retrieval systems is a plus.
• Experience serving graphs into retrieval or reasoning systems.
• Familiarity with neuro-symbolic AI and how structure supports reasoning.
• Experience with embeddings, vector search, and hybrid retrieval.
• Experience integrating CRM, AMS, or knowledge-base sources.
• Domain understanding of knowledge-intensive or professional communities.

Skills

Required

• Knowledge graph and ontology engineering
• Data pipeline and orchestration tools
• Python and SQL as primary languages
• Cloud data platforms and storage

Benefits

• Base Salary: $204,000 - $216,000 + early stage equity
• Generous health and wellness benefits