Semantic AI Engineer
- Milwaukee, Wisconsin, United States; Austin, Texas, United States; Houston, Texas, United States; Mayfield Heights, Ohio, United States
- Full-time
- Posted
Skills
Job description
Rockwell Automation is a global technology leader focused on helping the world’s manufacturers be more productive, sustainable, and agile. With more than 28,000 employees who make the world better every day, we know we have something special. Behind our customers - amazing companies that help feed the world, provide life-saving medicine on a global scale, and focus on clean water and green mobility - our people are energized problem solvers that take pride in how the work we do changes the world for the better.
We welcome all makers, forward thinkers, and problem solvers who are looking for a place to do their best work. And if that’s you we would love to have you join us!
Job Description
Job Description
Rockwell Automation is looking for an experienced Semantic AI Engineer to build the knowledge foundation that our enterprise AI agents depend on. This role sits within our AI Engineering organization and focuses on how agents remember, reason over, and share what the company knows. You will design and build a corporate knowledge graph that agents both draw from and contribute to, along with the agentic memory systems that let agents keep context across tasks, users, and time. You have a proven track record of modeling complex business domains, building production knowledge graphs or semantic layers, and connecting them to LLM-based applications.
This is a Hybrid role. You will report to the Director of Agentic AI.
Your Responsibilities
Key Technical Skill Expectations
Knowledge Graphs & Semantic Modeling: Design ontologies and graph schemas using property graph (e.g., Neo4j, Amazon Neptune, Azure Cosmos DB for Apache Gremlin) and/or RDF/OWL approaches, with query languages such as Cypher, Gremlin, or SPARQL. Apply entity resolution, schema alignment, and graph data quality techniques.
Agentic Memory: Architect memory layers for AI agents, including working memory, episodic and semantic long-term memory, memory consolidation and retrieval, and shared memory across multi-agent systems, using frameworks such as LangGraph, Mem0, Zep/Graphiti, Hindsight, LLMWiki etc.
Corporate Knowledge Graph for Agents: Build a living, agent-writable knowledge graph with provenance, trust levels, versioning, and conflict resolution so that knowledge produced by agents can be reviewed, trusted, and reused across the enterprise.
GraphRAG & Retrieval: Implement retrieval pipelines that combine knowledge graph traversal with vector search (e.g., Azure AI Search, pgvector, Redis) and embeddings to deliver accurate, explainable context to LLMs.
Semantic Layer & Open Standards: Understand semantic layers and metric definitions, and how open standards keep business meaning consistent as it moves between AI agents, BI platforms, and data tools.
Agent Integration & Security: Expose knowledge and memory services through MCP servers and APIs, with fine-grained access control, PII handling, and audit logging that comply with enterprise governance and security policies.
The Essentials - You Will Have
The Preferred - You Might Also Have
What We Offer
This position is part of a job family. Experience will be the determining factor for position level and compensation.
At Rockwell Automation we are dedicated to building a diverse, inclusive and authentic workplace, so if you're excited about this role but your experience doesn't align perfectly with every qualification in the job description, we encourage you to apply anyway. You may be just the right person for this or other roles.
#LI-Hybrid
#LifeAtRok
#LI-SB1
We are an Equal Opportunity Employer including disability and veterans.
If you are an individual with a disability and you need assistance or a reasonable accommodation during the application process, please contact our services team at 1 (844) 404-7247.
Rockwell Automation’s hybrid policy aligns that employees are expected to work at a Rockwell location at least Mondays, Tuesdays, and Thursdays unless they have a business obligation out of the office.