AI Engineer – Generative AI / RAG Systems + AZURE Cloud +.NET core

Role Overview

We are seeking a forward‑thinking AI Engineer to architect and deploy intelligent systems powered by Large Language Models (LLMs), Retrieval‑Augmented Generation (RAG), and advanced chunking strategies. The ideal candidate has deep experience in building scalable, production‑grade AI applications and integrating them into enterprise environments using Azure AI services.

Key Responsibilities

• Design and implement RAG pipelines using hybrid search (vector, keyword, semantic ranking, metadata enrichment)
• Apply chunking strategies (fixed‑size, recursive, semantic, agentic) to optimize document segmentation for retrieval/embedding
• Fine‑tune and evaluate LLMs (GPT, LLaMA, Ollama) for QA, summarization, NER, sentiment analysis
• Build multi‑agent systems with orchestration and agentic workflows
• Integrate AI capabilities into enterprise apps using Azure OpenAI, Cognitive Search, Azure Functions, Power Automate
• Collaborate with stakeholders to translate business needs into scalable AI solutions
• Ensure model reliability, performance, and ethical compliance across deployments

Mandatory Skills

• .NET Core
• Azure Functions
• Generative AI / OpenAI
• Vector Databases (Pinecone, FAISS)
• Python programming
• Azure AI Studio, Azure Cognitive Services
• Chunking techniques & embedding strategies
• MLOps tools (MLflow, Docker, CI/CD pipelines)
• Prompt engineering & model evaluation
• Familiarity with agentic systems & multi‑agent orchestration

Preferred Skills

• Experience with enterprise integrations (Power Automate, workflow engines)
• Knowledge of compliance and ethical AI frameworks
• Experience in productionizing AI systems with observability and monitoring