Job Description & Details
This is a hands-on architectural role for someone who knows how to bridge traditional enterprise backend systems with modern generative AI workloads. You aren't just drawing diagrams here; you're expected to build robust RAG pipelines and deploy scalable .NET 8 applications on Azure.
What You'll Actually Be Doing
You will spend your days bridging the gap between high-level system requirements and ground-level execution, specifically focusing on integrating LLMs into existing enterprise frameworks. Expect to design and review complex .NET, Azure, and RAG-based applications while untangling data indexing bottlenecks with Azure AI Search and ensuring your APIs can handle heavy workloads through Azure API Management.
The Core Tech Stack
You need absolute mastery over C#, .NET 8, and ASP.NET Core because the core backend relies heavily on them. Beyond traditional backend development, you must have hands-on production experience with Azure OpenAI, Azure AI Search, and building out serverless logic via Azure Functions to support retrieval-augmented generation architectures.
Interview Expectations
Expect the interviewers to probe deeply into your architectural choices around RAG, likely asking how you handle chunking strategies and semantic caching to reduce token latency and costs in Azure OpenAI. They want to see if you can defend your infrastructure design decisions when scaling a .NET 8 API alongside a heavy vector search workload.
Application Advice
Skip the generic architectural buzzwords and tailor your resume to highlight concrete examples where you shipped .NET microservices alongside Azure AI components. Make sure terms like RAG, Azure AI Search, Azure Functions, and .NET 8 are front and center so your profile easily sails through the automated filters.