AI Engineer
First seen by Alion on Nov 8, 2026.
We are looking for a skilled AI Engineer with a strong background in .NET backend development and AI-Native Software Architecture to design, develop, and integrate intelligent capabilities into enterprise applications.
The ideal candidate should understand how to build the complete software architecture surrounding Large Language Models (LLMs), transforming AI models into secure, scalable, observable, and production-ready business solutions.
This role is not focused on training AI models from scratch. Instead, it focuses on LLM integration, AI orchestration, context engineering, retrieval, memory, guardrails, and building robust .NET services around AI models.
Key Responsibilities
Design and implement AI-Native Software Architecture using C#, ASP.NET Core, and .NET.
Build modular AI application layers integrating LLMs with enterprise systems.
Develop AI orchestration services, prompt management, context engineering, and conversation memory components.
Implement Retrieval-Augmented Generation (RAG) solutions using vector databases, embeddings, and semantic search.
Build AI agents capable of tool calling, function execution, and integration with internal business APIs.
Develop secure API layers connecting LLM providers such as OpenAI, Azure OpenAI, and other hosted or local models.
Implement AI guardrails, input/output validation, access controls, and responsible AI mechanisms.
Design observability and monitoring capabilities for AI requests, token usage, latency, cost, and model performance.
Build AI evaluation and testing mechanisms to assess response quality, accuracy, and reliability.
Integrate AI services with existing enterprise applications, databases, and business workflows.
Apply clean architecture, SOLID principles, and modern software engineering practices.
Collaborate with software architects, backend developers, and product teams to deliver production-ready AI solutions.
Requirements
Must-Have Skills
3+ years of professional software development experience, with strong hands-on experience in C# and ASP.NET Core.
Solid understanding of Clean Architecture, layered architecture, REST APIs, dependency injection, and microservices.
Practical experience integrating LLMs through APIs such as OpenAI or Azure OpenAI.
Understanding of AI-Native Architecture and the software components surrounding LLMs.
Experience with prompt engineering, context management, and structured LLM outputs.
Knowledge of RAG, embeddings, vector search, and document retrieval.
Familiarity with AI agents, function calling, and tool integration.
Strong knowledge of SQL Server and database integration.
Understanding of authentication, authorization, API security, and secure AI integration.
Experience with Git and modern development workflows.
Preferred / Nice-to-Have Skills
Microsoft Semantic Kernel, Microsoft Agent Framework, or similar AI orchestration frameworks.
LangChain, LangGraph, or comparable agent frameworks.
Azure AI Foundry and Azure AI Search.
Vector databases such as Qdrant, Pinecone, Weaviate, or PostgreSQL with pgvector.
Model Context Protocol (MCP).
Multi-agent orchestration and agent workflows.
AI evaluation frameworks, tracing, and OpenTelemetry.
Redis for caching and conversation memory.
Docker, CI/CD, and cloud deployment.
Experience with local LLMs using Ollama or similar technologies.
Knowledge of AI security, prompt injection prevention, and data privacy.
What We're Looking For
We are particularly interested in engineers who understand that building an AI application is much more than sending a prompt to an LLM API.
You should be able to architect and implement the software layers that make AI reliable, secure, maintainable, and useful within real enterprise applications.
An ideal candidate can take an existing .NET business application and transform it into an AI-Native application by designing and implementing the required AI integration, orchestration, retrieval, memory, security, and observability components.