Principal AI Ops Engineer: Production ML & LLM Reliability

Tanqeeb; Abu Dhabi; On-site; AED 320,000 - 480,000; Full time

Job summary

Tanqeeb in Abu Dhabi is seeking a Principal AI Ops Engineer to own production AI systems, covering inference, deployment, observability, and reliability. You will set standards for efficient, safe AI operations at scale.

The role requires hands-on GPU-based inference expertise, Kubernetes, IaC, and strong Python engineering skills, with a focus on cost and performance optimization for enterprise AI workloads.

Qualifications

• Proven senior IC with staff/principal level in production ML/LLM.
• Hands-on GPU-based inference and model serving experience.
• Deep knowledge of batching, quantisation, latency and throughput.
• Strong AI/LLM observability, tracing and drift detection.
• Reliability engineering: SLOs, incidents, capacity planning.
• Hands-on Python for automation and tooling in production.
• Kubernetes, Docker and IaC across cloud environments.
• Experience with Azure and secure production environments.

Responsibilities

• Design, operate and optimise GPU inference and model-serving infrastructure.
• Optimise model serving latency, throughput, batching and costs.
• Build automated release pipelines for models and configurations.
• Establish AI observability across model, retrieval and orchestration layers.
• Define and maintain SLOs with automated alerts and post-mortems.
• Own capacity planning and cost optimisation for GPU/AI infra.
• Build secure, scalable Kubernetes environments and IaC patterns.
• Develop reusable deployment patterns and standards for AI systems.
• Lead complex production incidents and root-cause analysis.
• Provide technical leadership and engineering standards for AI systems.

Skills

GPU-based inference

Model serving

Python engineering

Kubernetes

Infrastructure as Code

Observability

Reliability engineering

FinOps awareness

Tools

Kubernetes

Docker

Terraform

Job description

Tanqeeb in Abu Dhabi is seeking a Principal AI Ops Engineer to own production AI systems, covering inference, deployment, observability, and reliability. You will set standards for efficient, safe AI operations at scale.

The role requires hands-on GPU-based inference expertise, Kubernetes, IaC, and strong Python engineering skills, with a focus on cost and performance optimization for enterprise AI workloads.