Senior MLOps Engineer

Open Data Science; Dubai; On-site; AED 223,200 - 334,800; Full time

Job summary

A fast-growing AI startup in Dubai seeks a Senior MLops Engineer to architect, deploy, and maintain scalable ML infrastructure on AWS. The candidate should have 2-3 years of experience with model serving frameworks, Kubernetes, and Python, to manage the high-performance serving stacks for large-scale models. This full-time role includes official employment and a relocation package.

Qualifications

• 2-3 years of experience with model serving frameworks.
• 2-3 years deploying LLMs and LDMs with GPU-aware scaling.
• 3-4 years experience with Kubernetes (EKS) and infrastructure-as-code.
• 4-5 years software engineering experience in Python.

Responsibilities

• Architect, deploy, and maintain scalable ML infrastructure on AWS EKS.
• Own end-to-end model deployment pipelines for LLMs and diffusion models.
• Design cost-effective auto-scaling serving systems.
• Build and maintain CI/CD pipelines integrating the ML model lifecycle.
• Optimize GPU resource utilization and implement job orchestration.

Skills

Model serving frameworks (Triton, vLLM, Ray Serve, TorchServe)

Kubernetes (EKS)

Terraform

Python

GPU optimization

Tools

AWS EKS

Helm

Prometheus

Grafana

KServe

Job description

Brief description of the vacancy

We are seeking aSenior MLops Engineerwith proven experience in deploying and managing large-scale ML infrastructure forLLMs,TTS,STT,Stable Diffusion, and otherGPU-intensive modelsin production. You will lead the design and operation ofcost-efficient,high-availability, andhigh-performanceserving stacks in a Kubernetes-based AWS environment.

About the company

Company Identity AI Labs

A fast-growing and well-funded AI startup in the UAE. Mission of the company is to redefine how humans interact with AI through emotionally intelligent, relationship-focused technology

Responsibilities

• You will architect, deploy, and maintain scalable ML infrastructure onAWS EKSusingTerraformandHelm.
• You will ownend-to-end model deploymentpipelines for LLMs, diffusion models (LDM/Stable Diffusion), and other generative/AI models requiringhigh GPU throughput.
• You will design cost-effective, auto-scaling serving systems using tools likeTriton Inference Server,vLLM,Ray Serve, or similar model-serving frameworks.
• You will build and maintain CI/CD pipelines integrating the ML model lifecycle (training → validation → packaging → deployment).
• You will optimize GPU resource utilization and implement job orchestration with frameworks likeKServe,Kubeflow, orcustom workloads on EKS.
• You will deploy and manageFluxCD(orArgoCD) for GitOps-based deployment and environment promotion.
• You will implement robust monitoring, logging, and alerting for model health and infrastructure performance (Prometheus, Grafana, Loki).
• You will collaborate closely with ML Engineers and Software Engineers to ensure smooth integration, observability, and feedback loops.

Requirements

• 2–3 yearsof experience with model serving frameworks such asTriton,vLLM,Ray Serve,TorchServe, or similar.
• 2–3 yearsof experience deploying and optimizingLLMsandLDMs(e.g., Stable Diffusion) under high load withGPU-aware scaling.
• 3–4 yearsof experience with Kubernetes (EKS) and infrastructure-as-code (Terraform, Helm).
• 4–5 yearsof hands-on software engineering experience inPython, with production-grade experience in ML model lifecycle.
• Nice to have: familiarity withGoorRustfor backend or performance-critical systems.

Working conditions

Full time job in Dubai office, official employment and full relocation package

Contacts

Log In Only registered users can open employer contacts.