Senior MLOps Engineer

What we offer

💲Salary fully aligned with your expectations

🚀Full relocation package to Dubai, customized to your needs

🇦🇪Official employment in the UAE

How You Will Influence the Workflow

▫️Architect and maintain scalable ML infrastructure on AWS EKS using Terraform and Helm.

▫️Lead end-to-end model deployment pipelines for LLMs, diffusion models, and other generative/AI models requiring high GPU throughput.

▫️Design cost-effective, auto-scaling serving systems using tools like Triton Inference Server, vLLM, Ray Serve, or similar.

▫️Build and maintain CI/CD pipelines integrating the ML model lifecycle

▫️Optimize GPU resource usage and implement job orchestration with frameworks like KServe, Kubeflow, or custom workloads on EKS.

▫️Deploy and manage FluxCD for GitOps-based deployment and environment promotion.

Implement robust monitoring, logging, and alerting.

Required Experience

▫️2–3 years with model serving frameworks like Triton, vLLM, Ray Serve, TorchServe, or similar.

▫️2–3 years deploying and optimizing LLMs and LDMs (e.g., Stable Diffusion) with GPU-aware scaling.

▫️3–4 years experience with Kubernetes (EKS) and infrastructure-as-code (Terraform, Helm).

▫️4–5 years of hands-on software engineering in Python, with ML model lifecycle experience.

▫️Fluent English