AI Engineer, Ontologies & Knowledge Graphs

Cadence Design Systems is seeking an AI Engineer focused on ontologies and knowledge graphs to build structured knowledge layers that enable Cadence product software surfaces to be understood and accessed programmatically. The role emphasizes ETL/ELT, semantic modeling, graph construction, and retrieval and indexing for downstream use.

Role Overview

You will develop ETL/ELT pipelines and knowledge graphs that represent product capabilities, enabling typed programmatic interfaces and data-access layers. This includes designing schemas, parsers, and retrieval/indexing mechanisms such as embeddings and RAG so downstream systems can consume product knowledge reliably across multiple products.

Key Responsibilities

• Build ETL/ELT pipelines that extract data from source code, APIs, file formats, and documentation, then load it into a structured knowledge store.
• Design and maintain schemas and semantic data models capturing entities, relationships, and capabilities.
• Construct and maintain knowledge graphs over heterogeneous product data.
• Develop source and metadata parsers, including source-code and AST parsing, to automatically extract structure.
• Implement typed programmatic interfaces and data-access layers over the knowledge layer.
• Build retrieval and indexing layers (for example, embeddings and RAG) over product knowledge.
• Collaborate with domain engineers to break down complex product workflows into discrete, callable operations.
• Evaluate data sources for coverage, quality, and schema completeness across multiple products.

Required Qualifications

• BS/MS in Computer Science, Mechanical Engineering, or similar.
• Strong Python and experience building and consuming REST APIs.
• Experience building data pipelines (ETL/ELT) over structured and unstructured data.
• Familiarity with graph databases and/or semantic and ontology modeling (RDF, OWL, property graphs, or equivalent).
• Experience with at least one agent framework: LangChain, LangGraph, AutoGen, CrewAI, or similar.
• Understanding of how LLMs consume context and call tools, including retrieval, RAG, and embeddings.
• Exposure to CAE/FEA/CFD or a related physical-simulation or engineering domain.
• Comfort working within unfamiliar or undocumented codebases.
• Systems thinker who can decompose a complex legacy workflow into discrete, callable steps.

Technologies

Python, REST APIs, ETL/ELT, graph databases, RDF, OWL, property graphs, LangChain, LangGraph, AutoGen, CrewAI, LLMs, retrieval, RAG, embeddings, CAE/FEA/CFD, AST parsing.

Nice to Have

• Vector databases.
• Data-access and API interface development.
• Parsing structured file formats.
• Surrogate modeling or related numerical methods.

Additional Notes

This role works across multiple products by building structured knowledge and interfaces over their capabilities. You will collaborate closely with domain engineers, who provide subject-matter expertise. Work includes data pipelines, graph databases, and product API surfaces. Travel is not expected; occasional travel may occur for broad team alignment workshops, but it is infrequent.

Location and Work Setting

Livonia, MI (onsite)