Role: Semantic Platform Engineer

Location: Boston, MA
Duration: 12 Months

Job Summary:

We are seeking an experienced Semantic Platform Engineer to design, develop, and maintain production-ready knowledge graph and ontology platforms that support AI-driven energy intelligence solutions. The engineer will build a semantic data layer that connects critical power equipment, asset relationships, and condition-based maintenance (CBM) analytics to enable diagnostic AI agents to generate standardized equipment health assessments, contextual insights, and prioritized maintenance recommendations.

The initial focus will be on data center power infrastructure, including Uninterruptible Power Supply (UPS) systems and busways. The solution will use historical, previously diagnosed customer data to develop and validate semantic models and diagnostic workflows, with Azure and Databricks supporting the underlying data platform.

Key Responsibilities:

• Deploy and configure the existing ontology engine and establish a centralized semantic repository accessible to collaborating engineering and partner teams.

• Design, develop, and maintain knowledge graphs, ontologies, and semantic data models representing equipment, asset dependencies, site structures, and operational relationships.

• Build and maintain data ingestion and transformation pipelines to load validated and resolved datasets into the semantic repository on Azure, integrating with existing Databricks-based CBM analytics.

• Develop portable and scalable deployment architectures using containers, infrastructure as code (IaC), and automated deployment practices to support future migration across cloud environments.

• Expose knowledge graph data to diagnostic AI agents through documented, secure, read-only query APIs and endpoints.

• Monitor and optimize semantic query performance, evaluating response times, scalability, and reliability.

• Manage ontology definitions, semantic mappings, and repository configurations as version-controlled code, following software engineering best practices.

• Implement automated ontology validation using SPARQL-based competency tests, SHACL constraints, and continuous integration (CI) pipelines.

• Develop and maintain technical documentation, ontology schemas, data mappings, schema summaries, and example queries to provide accurate context for AI-driven diagnostics.

• Define and maintain competency questions and expected answers to evaluate diagnostic agents against historical equipment incidents and previously validated customer data.

• Collaborate with domain experts, data engineers, software developers, and AI teams to translate business and equipment requirements into effective semantic models.

• Document ontology design decisions, asset relationships, modelling assumptions, and data validation rules to ensure consistency across teams.

• Support integration between knowledge graphs, condition-monitoring analytics, and AI diagnostic workflows to improve equipment health assessment and maintenance prioritization.

Required Qualifications:

• Minimum 4+ years of professional experience developing and deploying production-grade knowledge graphs, ontologies, or semantic data platforms.

• Strong hands-on experience with RDF, RDFS, OWL 2, SPARQL 1.1, and SHACL for semantic modelling, graph querying, ontology validation, and data conformance.

• Proficiency in Python, including libraries and frameworks such as rdflib , pySHACL , or equivalent semantic technology tools.

• Experience with Git-based version control, automated testing, and continuous integration workflows.

• Practical experience deploying, configuring, and operating RDF triple stores or semantic reasoning engines, such as GraphDB, Stardog, RDFox, or Apache Jena/Fuseki.

• Hands-on experience with Microsoft Azure, including containerized deployments, infrastructure as code, CI/CD pipelines, and cloud-based platform operations.

• Experience integrating semantic repositories with Azure Databricks and data engineering pipelines.

• Ability to work closely with domain specialists and communicate ontology design decisions clearly to software engineers and technical stakeholders.

• Strong problem-solving, analytical, documentation, and cross-functional collaboration skills.

Preferred Qualifications:

• Familiarity with electrical power distribution systems and data center infrastructure, including UPS equipment, busways, switchgear, and power distribution units (PDUs).

• Understanding of maintenance engineering concepts, including condition monitoring, equipment failure modes, Failure Mode and Effects Analysis (FMEA), and predictive maintenance.

• Experience applying industry-standard semantic vocabularies and ontologies, such as Brick, RealEstateCore, ASHRAE 223, SOSA/SSN, QUDT, ISO 14224, and IEC 81346.

• Experience integrating knowledge graphs with large language models (LLMs) using GraphRAG, text-to-SPARQL, ontology-grounded prompting, or similar approaches.

• Familiarity with property graph technologies such as Neo4j and Cypher, including the ability to evaluate property graph and RDF-based approaches for different use cases.

• Experience using ontology modelling and semantic development tools such as Protégé, TopBraid, or LinkML in enterprise environments.