Description

Role: 
The Senior Data & AI Engineer owns the full technical stack, including connectors, ingestion framework, OneLake Medallion staging, GraphDB triple store, Vector Index, Agentic RAG orchestrator, LLM gateway, guardrails, and the consumption UI with conversational chat, SPARQL trace explainability, and graph explorer.

Responsibilities:

• Develop and maintain graph databases (GraphDB, Neo4j, Stardog) in production or advanced PoC setups.
• Load, validate, and query ontologies within triple store environments.
• Collaborate with Data Consultants on ontology modeling using tools like Protégé or Metaphactory.
• Build and optimize RAG pipelines with agentic orchestration.
• Work with vector databases for embedding and retrieval tasks.
• Integrate LLM APIs (e.g., Anthropic Claude, OpenAI GPT, Azure OpenAI) with prompt engineering, guardrails, and citation mechanisms.
• Develop NL-to-SPARQL or NL-to-SQL generation solutions, employing few-shot prompting and schema grounding.
• Implement AI safety measures including prompt injection defenses, output sandboxing, and confidence scoring.
• Operate within an 8-week delivery cycle with weekly milestones.
• Collaborate closely with data modeling and ontologist teams.
• Leverage experience in financial services or insurance data environments where possible.

 Required Skills:

• 3+ years of hands-on experience with graph databases and semantic web standards.
• Proficiency in ontology authoring tools.
• Proven experience with RAG pipelines and agentic orchestration. 
• Expertise in vector databases and LLM API integration.
• Knowledge of NL-to-SPARQL/NL-to-SQL conversion techniques.
• Strong understanding of AI safety protocols.
• Project management skills suitable for rapid development cycles.
• Excellent collaboration and communication skills

Key Skills

Education

Any Graduate