Enterprise Semantic Architect for AI Knowledge Layer

Boehringer Ingelheim GmbH; Buenos Aires; On-site; ARS 181,906,000 - 272,860,000; Full time

Job summary

Boehringer Ingelheim GmbH is seeking an experienced AI Semantic Architect to design and operate the semantic foundation powering enterprise-scale AI, intelligent agents, and knowledge-driven applications.

You will build the Enterprise Semantic Layer, unify enterprise knowledge across domains, and engineer reusable components like semantic services, MCP servers, and agent tooling for scalable AI systems. Collaboration with data engineers and business stakeholders is essential.

Qualifications

• 5+ years of software engineering, backend engineering, data platforms, or AI platform development.
• Strong proficiency in Python and modern API development frameworks.
• Hands-on experience with RDF, OWL, SPARQL, and SHACL.
• Experience with knowledge graphs or semantic layer technologies.
• Familiarity with Git workflows, CI/CD, testing, and cloud-native architectures.

Responsibilities

• Design, build, and operate the Enterprise Semantic Layer for AI and knowledge-driven apps.
• Develop knowledge graph and semantic layer architectures using RDF/OWL/SHACL.
• Create retrieval solutions using graphs, embeddings, metadata, and semantic search.
• Integrate enterprise knowledge graphs with Snowflake, Databricks, Neo4j, and vector DBs.
• Define testing, monitoring, and governance for semantic AI systems.
• Develop MCP servers, semantic tools, and agent-facing services.

Skills

Python

API development

Knowledge graphs

Semantic web

MCP servers

Git workflows

CI/CD

Cloud-native

Stakeholder communication

Regulated environments

Tools

Stardog

Metaphactory

Snowflake

Databricks

Neo4j

Job description

Boehringer Ingelheim GmbH is seeking an experienced AI Semantic Architect to design and operate the semantic foundation powering enterprise-scale AI, intelligent agents, and knowledge-driven applications.

You will build the Enterprise Semantic Layer, unify enterprise knowledge across domains, and engineer reusable components like semantic services, MCP servers, and agent tooling for scalable AI systems. Collaboration with data engineers and business stakeholders is essential.