Senior MLOps Engineer Jobs in Abu Dhabi

Are you an experienced MLOps professional looking for your next opportunity in the UAE? Marc Ellis is seeking a skilled Senior MLOps Engineer in Abu Dhabi to help develop, deploy, and manage advanced machine learning (ML) and large language model (LLM) infrastructure.

This opportunity is suitable for professionals with strong expertise in AI infrastructure, cloud platforms, model serving, GPU optimization, and production-grade machine learning systems. The successful candidate will work across cloud and on-premises environments, focusing on scalable deployments, automation, performance, and operational reliability.

The position is offered on a 12-month contract, with the possibility of extension.

Senior MLOps Engineer Job Details

• Company Name: Marc Ellis
• Job Title: Senior MLOps Engineer
• Job Location: Abu Dhabi, UAE
• Contract Duration: 12 months, extendable
• Experience Required: 5–10 years
• Application Email: jila.a@marc-ellis.com

Role Overview

The Senior MLOps Engineer will be responsible for building and maintaining reliable infrastructure for machine learning models and large language models. The role requires practical experience in deploying AI workloads, optimizing inference performance, and managing ML platforms across cloud-based and customer-hosted environments.

Candidates should have a strong understanding of modern model-serving technologies, containerized infrastructure, GPU-based computing, and automated deployment workflows.

Experience operating AI systems in production environments is particularly relevant to this position.

Key Responsibilities

The role focuses on the following areas:

• Developing and operating production-ready infrastructure for machine learning and LLM applications.
• Deploying and managing model-serving solutions across cloud and on-premises environments.
• Improving inference performance and resource utilization for GPU-based workloads.
• Building scalable infrastructure using containers and Kubernetes.
• Automating infrastructure provisioning, deployment, and operational processes.
• Supporting reliable ML platform operations, model monitoring, and production performance.
• Managing deployments in restricted or offline environments where required.

These responsibilities are based on the role description and the technical capabilities specified in the vacancy announcement.

Required Qualifications and Technical Skills

Candidates should have the following experience and technical knowledge.

1. MLOps and ML Infrastructure

• Between 5 and 10 years of experience in MLOps, ML infrastructure, or ML platform engineering.
• Hands-on experience building and operating machine learning platforms.
• Knowledge of deploying and maintaining production ML and LLM workloads.

2. LLM Inference and Model-Serving Technologies

Practical experience with one or more of the following technologies is required:

• vLLM
• SGLang
• TensorRT-LLM
• NVIDIA Triton Inference Server
• Text Generation Inference (TGI)

Candidates should be familiar with model-serving architectures and techniques for improving inference performance.

3. Cloud and Container Infrastructure

Applicants should have expertise in at least one of the following cloud platforms:

• Amazon Web Services (AWS)
• Microsoft Azure
• Google Cloud Platform (GCP)

Strong experience with Kubernetes, Docker, GPU infrastructure, and model serving is also required.

4. Automation and MLOps Tooling

The vacancy highlights experience with the following tools and technologies:

• Python
• MLflow or Kubeflow
• Terraform
• CI/CD pipelines

These skills support automated deployments, reproducible workflows, infrastructure management, and reliable ML operations.

5. Advanced Deployment and Optimization Experience

Experience deploying ML and LLM platforms in both SaaS and customer on-premises environments is an important requirement.

Additional experience that can strengthen an application includes:

• Air-gapped and offline infrastructure deployments.
• GPU performance optimization.
• Distributed inference systems.
• Model monitoring and operational observability.
• Production-level LLM infrastructure management.

Air-gapped deployment experience and advanced GPU or distributed inference expertise are highlighted as valuable advantages.

How to Apply for the Senior MLOps Engineer Position

Interested candidates with relevant MLOps and AI infrastructure experience can submit their CV directly to the recruitment contact provided in the announcement.

Application Email: jila.a@marc-ellis.com