Senior AI Engineer; m​/f​/d

Role Overview

We are seeking a Senior AI Engineer to take end-to-end technical ownership of one or more agentic automation use cases within a leading UAE financial institution's AI Centre of Excellence. You will lead the delivery of complex Lang Graph multi‑agent pipelines, drive confidence calibration and HITL threshold strategy, and mentor AI Engineers across the team. This is a hands‑on leadership role where you define architecture within your domain, identify production failure modes early, and advance the adoption of new AI capabilities across a growing use case portfolio.

• Use case technical ownership: Own the technical delivery of one or more AWA use cases from discovery through production; define Agent Profile, Use Case Manifest, Data Manifest, and Tool Authorisation Matrix.
• Architecture and design: Design Lang Graph agent graph topologies for complex multi‑agent pipelines including Supervisor-Worker fan‑out, parallel execution, state compression, and cross‑document reconciliation.
• Confidence calibration and HITL thresholds: Lead AI Metric Baselines calibration; measure ECE, derive HITL routing thresholds empirically, and present recommendations to business and risk teams.
• Test strategy ownership: Own and execute the full AI IDP Test Strategy for your use cases across all testing bands through to sign‑off.
• Agent Regression Testing: Maintain Golden and Regression Datasets; configure CI/CD regression pipeline gates; review results after every model or prompt change.
• Mentoring and code review: Mentor AI Engineers; conduct substantive technical code reviews of agent graphs, prompts, and MCP tool implementations; maintain coding standards.
• Stakeholder engagement: Present model quality metrics, STP rates, and HITL rates to business owners; recommend threshold adjustments with data‑backed rationale.
• New capability adoption: Evaluate and prototype new AI capabilities for incorporation into the AWA accelerator catalogue.

• 5+ years Python development; 2+ years in production AI/ML engineering.
• Deep Lang Graph or equivalent agentic framework experience: graph topology, state management, conditional edges, checkpoint‑based recovery.
• LLM evaluation expertise: F1 measurement, Expected Calibration Error (ECE), hallucination detection, confidence calibration.
• Prompt engineering at scale: versioned prompts, sensitivity analysis, few‑shot dataset curation.
• RAG architecture: hybrid retrieval (BM25 + vector), re‑ranking, chunk citation, grounding verification.
• Azure AI Foundry or equivalent LLM inference platform: token budget management and APIM integration.
• Workflow orchestration: Orkes Conductor or Temporal — HITL wait tasks, retry policies, compensating transactions.
• CI/CD pipeline integration for ML: Azure Dev Ops, MLflow experiment tracking, model registry promotion.
• Bachelor's degree in Computer Science, AI/ML, or equivalent;
  Master's preferred.

• Computer vision model deployment and evaluation experience.
• Azure AI Document Intelligence: form recogniser, custom models, layout analysis.
• Kubernetes / AKS: workload identity, namespace isolation, KEDA autoscaling.
• Banking domain knowledge: cheque clearing, trade finance, KYC, AML.
• Azure AI Engineer Associate or equivalent certification.
• Demonstrable production AI deployments with case studies or public work.

We encourage applications from all qualified candidates, regardless of race, gender, disability, or any other characteristic that makes them unique.