Dubai AI Infra & Platform Engineer (Kubernetes + GPUs)

Tech Junction Ltd; Dubai; On-site; AED 350,000 - 600,000; Full time

Job summary

Systemsltd seeks an experienced DevOps/Infrastructure/SRE/Platform Engineer in Dubai to lead AI infra, Kubernetes orchestration, GPU provisioning, and robust CI/CD workflows. You will collaborate with platform teams and architects to ensure high availability and low latency for enterprise AI systems.

Ideal candidates have 5+ years in DevOps/SRE, deep Kubernetes and cloud know-how, Prometheus/Grafana expertise, and hands-on management of Azure, PostgreSQL, and Linux environments.

Qualifications

• Bachelor’s or Master’s degree in a technical field.
• 5+ years in DevOps/SRE/Infrastructure/platform engineering.
• Strong Kubernetes and cloud DevOps proficiency.
• GPU hardware management for ML/LLM pipelines.
• Prometheus/Grafana monitoring experience.
• Azure Cloud, PostgreSQL, Linux expertise.
• Experience with Ollama/vLLM and n8n.

Responsibilities

• Design and operate enterprise AI infra on Kubernetes.
• Manage NVIDIA GPU clusters and accelerators for ML workloads.
• Build and troubleshoot LLM pipelines and model serving.
• Configure and maintain observability stacks (Prometheus, Grafana).
• Administer Azure cloud infrastructure, VNet, IAM and storage.
• Deploy local LLM runtimes (Ollama, vLLM) and serving engines.
• Automate workflows with n8n and IaC tools.
• Manage PostgreSQL databases for high-throughput apps.
• Drive CI/CD pipelines and release automation.
• Perform incident response and RCA for high availability.

Skills

Kubernetes

Prometheus

Grafana

Azure Cloud

PostgreSQL

Linux

CI/CD

RCA

GPU hardware

Education

Bachelor's or Master's degree

Tools

Ollama

vLLM

n8n

Terraform

Ansible

Kubernetes

Job description

Systemsltd seeks an experienced DevOps/Infrastructure/SRE/Platform Engineer in Dubai to lead AI infra, Kubernetes orchestration, GPU provisioning, and robust CI/CD workflows. You will collaborate with platform teams and architects to ensure high availability and low latency for enterprise AI systems.

Ideal candidates have 5+ years in DevOps/SRE, deep Kubernetes and cloud know-how, Prometheus/Grafana expertise, and hands-on management of Azure, PostgreSQL, and Linux environments.