Job Description & Details
This is a heavy-hitting AI/ML engineering role that bridges the gap between modern generative AI workflows and enterprise .NET backend systems. You won't just be tinkering with LLM prompts all day; you'll be actively embedding intelligence into core .NET microservices and scaling production-grade AI solutions.
What You'll Actually Be Doing
Expect to spend your days designing, building, and deploying AI-powered applications where about 80% of your focus is purely on Generative AI, LLMs, and agentic workflows. You will be writing Python for the AI model integrations while heavily leveraging your C# and .NET Core skills to wire those capabilities into robust enterprise architectures. You'll deal directly with vector databases, embeddings, and Retrieval-Augmented Generation (RAG) pipelines to ensure the LLM responses are accurate, contextual, and performant.
The Core Tech Stack
You need absolute fluency in Azure OpenAI, OpenAI APIs, and advanced prompt engineering techniques, combined with hands-on experience building RAG architectures and AI agents. On the backend, strong C#, .NET Core, ASP.NET Core, and Web API knowledge is non-negotiable since you'll be exposing and consuming these AI features within microservices. Python is required for your AI tooling, while familiarity with Azure AI, Azure ML, SQL, Git, CI/CD, and Docker/Kubernetes will make your transition into their deployment pipeline seamless.
Interview Expectations
Expect the interview panel to grill you on your architectural choices for RAG and vector database optimization, likely asking how you handle chunking strategies and latency reduction when querying massive embedding spaces. They want to see if you truly understand the failure modes of LLMs in production, so be prepared to discuss how you implement fallback mechanisms, guardrails, and deterministic validation layers around non-deterministic AI outputs.
Application Advice
Your resume needs to heavily feature concrete metrics and examples of production-level Generative AI deployments, particularly where you successfully integrated Python-based AI microservices with enterprise .NET architectures. Make sure your keywords explicitly highlight Azure OpenAI, RAG, Vector Databases, C#, and .NET Core so your application sails past the ATS and lands directly on the engineering manager's desk.