Senior AI Engineer

Allstate Allstate · Insurance · IL · Remote

Senior AI Engineer to build an enterprise Semantic Ontology & Dimension Factory Platform. This platform combines semantic ontologies, knowledge graphs, and agentic AI to generate business-ready star schemas from enterprise data. The role involves designing and implementing agent-driven pipelines using LLMs and semantic technologies (RDF/OWL, SPARQL) for data modeling and alignment, as well as building Python microservices and data pipelines on Microsoft Fabric.

What you'd actually do

  1. Design, build, and maintain agentic AI pipelines (using Google ADK or similar frameworks) to automate semantic mapping, dimension mining, and ontology‑driven reasoning.
  2. Create and evolve enterprise ontologies in RDF/OWL, including upper ontologies and domain extensions aligned to CIM (where applicable), to enable reusable enterprise semantics.
  3. Engineer LLM‑powered services for schema understanding, semantic alignment, ontology enrichment, and AI‑assisted metadata generation, with a focus on accuracy, traceability, and scale.
  4. Implement SPARQL querying and reasoning layers over knowledge graphs to drive downstream transformations and ensure consistent interpretation of business concepts.
  5. Architect and deliver Python‑based microservices and batch pipelines that integrate semantic reasoning with modern data‑engineering workflows.

Skills

Required

  • Python
  • GenAI
  • LLM-based systems
  • RDF
  • OWL
  • ontologies
  • knowledge graphs
  • SPARQL
  • agentic AI frameworks
  • data engineering concepts
  • ETL/ELT
  • star schemas
  • metadata-driven pipelines
  • cloud platforms
  • Microsoft Azure
  • Microsoft Fabric

Nice to have

  • enterprise data models
  • CIM
  • canonical models
  • semantic alignment
  • ontology mapping
  • data cataloguing tools
  • MLOps
  • LLMOps
  • model evaluation
  • AI observability
  • distributed systems
  • CI/CD pipelines
  • containerisation
  • AI‑assisted analytics
  • semantic layers
  • BI
  • NLQ use cases

What the JD emphasized

  • strong proficiency in Python and GenAI
  • Hands-on experience building LLM‑based systems
  • Solid understanding of semantic technologies: RDF, OWL, ontologies, knowledge graphs, and SPARQL
  • Experience designing or working with agentic AI frameworks (e.g., Google ADK, LangChain agents, or similar)
  • Strong background in data engineering concepts (ETL/ELT, star schemas, metadata‑driven pipelines)

Other signals

  • design and implement agent-driven pipelines
  • leverage semantic ontologies, knowledge graphs, agentic AI
  • LLM-powered services for schema understanding, semantic alignment, ontology enrichment
  • Python-based microservices and batch pipelines that integrate semantic reasoning with modern data-engineering workflows