Senior Ontology Engineering Lead

About Grafton Sciences

We’re building AI systems with general physical ability — the capacity to experiment, engineer, or manufacture anything. We believe achieving this is a key step towards building superintelligence. With deep technical roots and real-world progress at scale (e.g., a $42M NIH project), we’re pushing the frontier of physical AI. Joining us means inventing from first principles, owning real systems end-to-end, and helping build a capability the world has never had before.

About the Role

We’re seeking a Senior Ontology & Knowledge Graph Engineer to design, implement, and evolve the semantic structures that organize knowledge across autonomous systems and complex workflows. You’ll build ontologies, schemas, and graph-based representations that enable consistent interpretation, interoperability, and reasoning across agents, tools, and data sources.

This role focuses on knowledge modeling at system scale: defining meaning, constraints, and relationships that remain stable under continuous updates while supporting downstream reasoning, planning, and learning systems.

Responsibilities

• Design and maintain ontologies and knowledge graph schemas that represent entities, relations, events, and processes across complex domains.

• Implement graph-based knowledge systems (property graphs, RDF/OWL, or hybrid approaches) that support querying, inference, and evolution over time.

• Define semantic constraints, typing systems, and validation rules to ensure consistency, correctness, and interpretability of knowledge.

• Build ingestion and update mechanisms that integrate heterogeneous data sources into unified semantic representations.

• Collaborate with agents, ML, and systems teams to ensure knowledge representations are usable by planners, reasoning engines, and learning systems.

• Develop tooling for ontology evolution, versioning, alignment, and impact analysis as schemas and domains change.

• Support reasoning and decision pipelines by enabling symbolic queries, rule-based inference, or hybrid neuro-symbolic integration.

• Act as a cross-functional technical partner, translating domain knowledge into formal structures and ensuring semantic layers scale with system complexity.
  

Qualifications

• Strong background in ontology engineering, knowledge representation, semantic modeling, or knowledge graphs.

• Experience designing and implementing ontologies or schemas for complex domains (e.g., processes, workflows, scientific data, enterprise systems).

• Familiarity with graph data models and technologies (e.g., RDF/OWL, SPARQL, property graphs, Neo4j, TigerGraph, or similar).

• Understanding of computational logic, typing systems, constraints, or rule-based inference.

• Comfort working alongside ML and data systems, and bridging symbolic semantics with statistical or learned components.

• Experience designing abstractions that support large-scale, evolving, real-time knowledge updates.

• High-agency engineer who enjoys defining structure in ambiguous domains and building semantic systems from first principles.

• MS degree (or equivalent) required. PhD preferred.

Above all, we look for candidates who can demonstrate world-class excellence.

Compensation

We offer competitive salary, meaningful equity, and benefits.