MLOps Engineer: Kubernetes AI Deployment & Observability

Business Umbrella; Abu Dhabi; On-site; AED 120,000 - 180,000; Full time

Job summary

A leading tech company in Abu Dhabi is seeking an experienced AI/ML Infrastructure Engineer to operate Kubernetes/OpenShift clusters and manage LLMs and other AI models. The ideal candidate has at least 3 years of experience in DevOps or MLOps roles, with proven skills in deploying and scaling models, and automating CI/CD pipelines. This role involves ensuring high availability and performance of AI services in production, offering a competitive salary for individuals with a strong technical background.

Qualifications

• 3 years experience in DevOps, MLOps or AI/ML infrastructure roles.
• Proven experience with Kubernetes or OpenShift in production environments.
• Strong scripting skills in Python and Bash.

Responsibilities

• Operate and manage Kubernetes or OpenShift clusters.
• Deploy and manage LLMs and AI models for inference.
• Automate CI/CD pipelines for model retraining and rollback.

Skills

Kubernetes

OpenShift

CI/CD automation

Python

Linux system administration

Monitoring tools (Prometheus, Grafana)

Tools

MLFlow

GitLab CI

Triton Inference Server

Job description

A leading tech company in Abu Dhabi is seeking an experienced AI/ML Infrastructure Engineer to operate Kubernetes/OpenShift clusters and manage LLMs and other AI models. The ideal candidate has at least 3 years of experience in DevOps or MLOps roles, with proven skills in deploying and scaling models, and automating CI/CD pipelines. This role involves ensuring high availability and performance of AI services in production, offering a competitive salary for individuals with a strong technical background.