Staff AI Platform Engineer

About the role

The organization is launching a large‑scale AI transformation for public services in Abu Dhabi. As a Staff AI Platform Engineer you will own the core infrastructure that lets engineering teams develop, serve, and monitor AI models at government scale.

Key responsibilities

• Design, build, and operate model‑serving stacks using technologies such as vLLM, TGI, or TensorRT‑LLM.
• Develop and manage vector databases, embedding pipelines, and retrieval systems.
• Create data pipelines for document ingestion, transformation, and storage.
• Own CI/CD pipelines, deployment platforms, and infrastructure‑as‑code (Terraform).
• Implement observability across the AI stack, define SLOs, and lead capacity‑planning and reliability initiatives.
• Lead incident response, root‑cause analysis, and post‑mortems.
• Build reusable SDKs, internal tooling, and deployment patterns for other engineering teams.
• Mentor engineers and set technical standards for security, scalability, and performance.

Required profile

• 10+ years of platform, infrastructure, or backend engineering experience.
• Proven experience at staff or principal engineer level.
• Deep expertise in Azure (AWS or GCP also valued).
• Strong Kubernetes and Docker skills.
• Hands‑on experience with Terraform, CI/CD pipelines, and infrastructure‑as‑code.
• Experience building production‑grade data pipelines.

Required skills

• Azure, AWS, GCP
• Kubernetes, Docker
• Terraform
• CI/CD pipelines
• Infrastructure‑as‑code
• vLLM, TGI, TensorRT‑LLM
• Vector databases and embedding pipelines
• Data ingestion and transformation pipelines
• Observability tools and SLO definition
• Incident response and post‑mortem analysis
• SDK and internal tooling development
• AI coding assistants such as Codex or Claude Code