AI Engineer – Azure OpenAI & Retrieval Systems; RAG

AI Engineer – Azure OpenAI & Retrieval Systems (RAG)

We have an urgent requirement for an AI Engineer specialized in Azure OpenAI & Retrieval Systems (RAG) for our banking client in Abu Dhabi, UAE. The role demands strong experience designing and building RAG systems end-to-end, along with Azure OpenAI Service, Azure AI Search (Vector + Semantic Search), and AI application engineering in Python and APIs.

• Design, develop, and deploy end-to-end AI solutions using Azure OpenAI, Azure AI Search, and RAG architectures.
• Build and maintain Retrieval-Augmented Generation (RAG) pipelines, including document chunking, embeddings, vector indexing, and retrieval strategies.
• Develop scalable and secure data ingestion pipelines for structured and unstructured data from multiple sources.
• Implement semantic search solutions using Azure AI Search, vector search, and hybrid search approaches.
• Design and manage prompt orchestration frameworks, including prompt templates, versioning, chaining, and evaluation.
• Build LLM‑powered applications (chatbots, copilots, assistants, APIs) with strong grounding, relevance, and factual accuracy.
• Ensure performance optimization, low latency, and cost efficiency for AI workloads.
• Apply security best practices, including data privacy, access controls, encryption, and responsible AI principles.
• Implement techniques to reduce hallucinations and improve model grounding using retrieved enterprise data.
• Monitor, evaluate, and continuously improve model responses using metrics, logging, and feedback loops.
• Collaborate with product, data, and cloud engineering teams to integrate AI solutions into existing systems.
• Deploy AI solutions to production using Azure‑native services, following Dev Ops and MLOps best practices.

• Strong hands‑on experience with Azure OpenAI Service.
• Proven experience implementing Retrieval‑Augmented Generation (RAG) in production environments.
• Expertise with Azure AI Search, including vector search and semantic ranking.
• Experience with embeddings, chunking strategies, and vector databases.
• Strong proficiency in Python (mandatory).
• Experience building REST APIs and backend services for AI applications.
• Knowledge of prompt engineering, prompt chaining, and LLM orchestration frameworks.
• Experience with Azure cloud services (App Services, Functions, Storage, Key Vault, Identity, etc.).
• Understanding of LLM limitations, grounding techniques, and hallucination mitigation.
• Familiarity with CI/CD, Dev Ops, and MLOps practices in Azure environments.