Senior GenAI​/RAG Engineer — Enterprise Azure AI; Hybrid

Seeking Senior AI Engineers / Applied GenAI Engineers!

Location
:
Phoenix, AZ preferred (hybrid/on-site)

Duration
:
Initial 6-month engagement

Engagement Type
:
Contract

We are unable to partner with third parties at this time.

We are seeking an experienced Applied AI Engineer / Generative AI Engineer to accelerate the production readiness and enterprise modernization of an internal AI assistant platform ( "Sage") supporting store operations. This platform delivers intelligent SOP guidance and product knowledge access for in-store teams across departments such as deli, bakery, pharmacy, and wellness. The ideal candidate has hands‑on experience designing, optimizing, and product ionizing Retrieval‑Augmented Generation (RAG) applications in Microsoft Azure environments.

• Design, optimize, and product ionize enterprise RAG architectures
• Improve retrieval accuracy, classification logic, and orchestration workflows
• Refactor existing monolithic AI application into scalable enterprise architecture
• Build and enhance multi-agent orchestration using Lang Graph or similar frameworks
• Integrate structured and unstructured data sources including:
  • SOP documentation
  • Product metadata (Postgre
    
    SQL)
  • Wellness / vitamin knowledge sources
• Implement Azure AI Search indexing and vector search optimization
• Develop APIs and backend services using FastAPI / Python
• Integrate with Microsoft Azure AI services including:
  • Azure AI Foundry
  • Azure OpenAI
  • Azure AI Search
• Improve prompt engineering, grounding, hallucination controls, and answer governance
• Support voice-to-text integration for tablet‑based user workflows
• Collaborate with product and engineering stakeholders to product ionize the platform

• 3–7+ years software engineering experience
• 2+ years applied Generative AI / LLM implementation
• Strong hands‑on RAG development experience
• Azure AI Search expertise
• Azure AI Foundry / Azure OpenAI experience
• Python development (required)
• FastAPI
• Vector databases / embeddings / retrieval tuning
• Lang Graph or multi‑agent orchestration frameworks
• API integration design
• PostgreSQL
• Prompt engineering / grounding techniques
• Experience troubleshooting retrieval quality issues

• C# / .NET ecosystem familiarity
• Voice AI / speech‑to‑text integration
• Retail operations / knowledge assistant experience
• Enterprise AI governance / responsible AI controls
• Copilot / Claude / Cursor exposure