AI Full Stack Engineer, Ontologies & Knowledge Graphs (Agentic AI, Surrogates, Physical AI)
All the best with your application!
Want more jobs like this straight to your inbox?
Get Job Alerts
Get a curated list of the top robotics roles delivered straight to your inbox each week. We sift through hundreds of postings to find the high-salary positions, leading companies, and remote opportunities you actually want.
Unsubscribe anytime. We respect your privacy.
Summary
pune, India
Full-time
6+ years
About this Job
At Cadence, we hire and develop leaders and innovators who want to make an impact on the world of technology.
AI Full Stack Engineer, Ontologies & Knowledge Graphs (Agentic AI, Surrogates, Physical AI) —
Exp: 6+yrs
Job Location: Pune
Summary: Makes our simulation products AI-accessible. Our products have rich programmatic surfaces — scripting APIs, file formats, data structures, workflow logic — that are powerful but not designed for AI consumption. This engineer defines the ontology schema that describes those surfaces, builds the knowledge graphs on top of them, and wraps them as structured, typed interfaces that AI agents can discover and invoke.
Responsibilities:
- Define and maintain ontology schemas describing product capabilities, entities, and relationships
- Build and maintain knowledge graphs over product documentation, APIs, and simulation data
- Build structured tool interfaces exposing product capabilities to AI systems
- Write connectors to product APIs, parsers, and data access layers
- Implement retrieval and context layers over product knowledge
- Work with domain engineers to translate simulation workflows into discrete, callable operations
- Review product ontologies for agentic-readiness across 2–3 products
Skills we need:
- Strong Python; experience building and consuming REST APIs
- Familiarity with graph databases and/or ontology/semantic 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
- Comfortable working within unfamiliar or undocumented codebases
- Systems thinker — able to decompose a complex legacy workflow into discrete, callable steps
Nice to have:
Vector databases; agent-tool interface development; parsing structured file formats; exposure to CAE/FEA/CFD, surrogate modeling, or physical AI.
Deliberately not required: Deep simulation domain knowledge — domain engineers provide that. No PhD or ML research background.
We’re doing work that matters. Help us solve what others can’t.
About the Company
