DevSecOps/Platform Engineer (AI Infra)

integra.works • United Arab Emirates
Relocation Remote
Apply
AI Summary

We are hiring an experienced DevSecOps/Platform Engineer for a fully remote role with a Dubai-based AI company. The position involves end-to-end ownership of production infrastructure, security, observability, and the deployment of self-hosted AI/ML models.

Key Highlights
Infrastructure & Production Readiness
CI/CD & Source Control setup
Kubernetes Cluster Engineering
Monitoring, Observability & Logging
Networking, Security & TLS configuration
Technical Skills Required
Kubernetes Linux Terraform Prometheus Grafana MinIO Cloudflare PostgreSQL MongoDB Kafka CUDA GPU
Benefits & Perks
Fully remote opportunity
Potential for relocation to the UAE in 2027

Job Description


Job Summary

We are hiring an experienced DevSecOps / Platform Engineer (DevSecOps + AI Infra) based in Egypt for a fully remote role with a Dubai-based AI company. The position involves end-to-end ownership of production infrastructure, security, observability, and the deployment of self-hosted AI/ML models across GPU and CPU environments. This is a fully remote opportunity, with potential for relocation to the UAE in 2027, subject to business needs and mutual interest.

Responsibilities

  • Infrastructure & Production Readiness including server sizing, subnetting, and firewalls.
  • CI/CD & Source Control setup using GitLab with secure pipeline management.
  • Kubernetes Cluster Engineering for cluster management and scaling.
  • Monitoring, Observability & Logging setup using Prometheus and Grafana.
  • Storage & Object Storage management using MinIO.
  • Networking, Security & TLS configuration with Cloudflare.
  • Containers & Image Management best practices.
  • Database management including PostgreSQL and MongoDB.
  • Kafka Readiness for high availability and monitoring.
  • Infrastructure as Code (Terraform) provisioning.
  • AI / ML / LLM Infrastructure deployment and management.

Qualifications

  • Minimum 4 years of relevant experience required; 6+ years strongly preferred.
  • Bachelor's in Computer Science or related field
  • Strong Kubernetes, Linux, networking, and Terraform expertise.
  • Experience with self-hosted AI/LLM models (Ollama, vLLM, TGI). Hands-on with GPU setups, CUDA, inference optimization.
  • Strong observability & security foundations.

Subscribe our newsletter

New Things Will Always Update Regularly