Principal AI Ops Engineer: Production GPU Inference

Discovered MENA; Abu Dhabi; On-site; AED 350,000 - 650,000; Full time

Job summary

Discovered MENA is partnering with a leading Abu Dhabi organization to recruit a Principal AI Ops Engineer. The role focuses on production AI systems, spanning inference, model serving, deployment, observability, reliability and performance.

You will shape operational standards for safe, reliable and efficient AI deployments. The position targets hands-on leaders who can set standards while remaining close to engineering and production systems, with responsibility for cost, capacity and incident

Qualifications

• Proven Staff/Principal level with production ML/LLM experience.
• Hands-on GPU-based inference and model serving expertise.
• Strong Python engineering for automation and tooling.

Responsibilities

• Design, operate and optimise GPU-based inference and model-serving infra for production AI and LLM workloads.
• Optimize model serving latency, throughput, batching and autoscaling while minimising cost.
• Build automated release pipelines for models, prompts and configurations with canaries and rollbacks.
• Establish AI observability across model, retrieval and orchestration layers.
• Define and maintain SLOs, alerts and incident response for AI systems.
• Own capacity planning and cost optimisation across GPU infrastructure.
• Develop reusable deployment patterns and tooling for reliable AI shipping.
• Lead complex production incidents, load testing and root-cause analysis.
• Provide technical leadership and establish engineering standards for AI systems at scale.

Skills

GPU inference

Model serving

Kubernetes

Python automation

Observability

Cost optimisation

Tools

Terraform

Langfuse

LangSmith

Grafana

Prometheus

Arize Phoenix

Job description

Discovered MENA is partnering with a leading Abu Dhabi organization to recruit a Principal AI Ops Engineer. The role focuses on production AI systems, spanning inference, model serving, deployment, observability, reliability and performance.

You will shape operational standards for safe, reliable and efficient AI deployments. The position targets hands-on leaders who can set standards while remaining close to engineering and production systems, with responsibility for cost, capacity and incident