AI Engineer M F D

Role Overview

We are seeking a talented AI Engineer to join a forward-thinking financial institution's AI Centre of Excellence in Abu Dhabi. As the primary builder within the Agentic Workflow Automation (AWA) team, you will design, build, and test LangGraph agent graphs, LLM extraction pipelines, prompt management workflows, and MCP tool integrations. Your work will power intelligent automation use cases — beginning with Intelligent Document Processing for banking operations — using a dual-layer orchestration stack (Orkes Conductor + LangGraph) and Azure AI Foundry to deliver production-grade agentic systems.

Key Responsibilities

• Agent graph development: Design and implement LangGraph agent graphs for Supervisor-Worker orchestration, self-reflection, actor-critic, and HITL interrupt patterns using TypedDict state schemas and conditional edge routing.
• LLM extraction pipeline: Build and maintain LLM-based entity extraction pipelines using Azure AI Foundry, implementing structured output enforcement, per-field confidence scoring, and Pydantic output validation.
• Prompt engineering and governance: Author, version, and govern prompts through the AWA Prompt Management System using semantic versioning; run prompt sensitivity and correctness testing.
• MCP tool integration: Develop and maintain core MCP tool servers and extend them for new use case requirements.
• Model evaluation and testing: Execute multi-band testing (Model, Prompt, Agent, AI Security, Adversarial) per the AWA IDP Test Strategy; maintain Golden Datasets and Regression Datasets.
• HITL framework: Implement Human-in-the-Loop interrupt calls at mandatory and dynamic review points in LangGraph graphs; configure wait tasks; validate state persistence and checkpoint-based resumption.
• AI guardrail integration: Integrate Azure AI Content Safety, PII detection and tokenisation, prompt injection shielding, and output sanitisation into agent pipelines.
• Cross-field validation rules: Implement business validation logic within LangGraph validation agent nodes.
  
  

• 5+ years of Python development in production environments.
• Hands-on experience with LangGraph, LangChain, or equivalent agentic AI frameworks.
• Practical LLM prompt engineering: structured outputs, few-shot design, output schema enforcement.
• Familiarity with Azure AI Foundry / OpenAI API or equivalent LLM APIs (Anthropic, Cohere).
• Understanding of agent design patterns: ReAct, self-reflection, tool use, and HITL.
• REST API development and consumption; JSON schema design.
• Git version control and CI/CD pipeline awareness.
• Bachelor's degree in Computer Science, AI/ML, Software Engineering, or related field.
  
  

• Experience with Orkes Conductor, Apache Airflow, or Temporal for workflow orchestration.
• Azure AI Document Intelligence or equivalent OCR platform experience.
• Knowledge of RAG architectures: chunking, vector indexing, Azure AI Search.
• Azure platform familiarity: AKS, ADLS Gen2, Azure ML, Azure Monitor.
• Pydantic, FastAPI, and/or TypeScript/Node.js proficiency.
• Master's degree or equivalent research/industry experience.
• Relevant Azure certifications (AI Engineer Associate, Developer Associate).
• Genuine intellectual curiosity about AI systems and their failure modes.