MLOps Engineer Senior On-site

#вакансия #vacancy #job #ML #MLOps #hiring Senior MLops Engineer for fast growing Startup in Dubai! ☀️ What we offer 💲 Salary: $7,000–10,000 net per month, depending on experience 🚀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 & Helm • Own end-to-end deployment pipelines for LLMs, diffusion, and generative models with high GPU load • Build and optimize high-load inference systems (image generation, TTS/STT) with strong performance focus • Design cost-efficient, auto-scaling serving using Triton, vLLM, Ray Serve, or similar • Integrate CI/CD across the ML lifecycle (training → deployment) • Optimize GPU utilization and orchestrate workloads via KServe, Kubeflow, or custom EKS solutions Manage GitOps deployments with FluxCD / ArgoCD • Ensure monitoring, logging, and alerting (Prometheus, Grafana, Loki) Collaborate closely with ML, Infra, and Engineering teams Required Experience • 4–5 years of extensive experience implementing inference systems and deploying ML models to production environments • 2–3 years of experience with model serving frameworks such as Triton, vLLM, Ray Serve, TorchServe, or similar • 3–4 years of experience deploying and optimizing LLMs or diffusion models under high load at scale with GPU-aware scaling • 3–4 years of experience with Kubernetes (EKS) and infrastructure-as-code (Terraform, Helm) • 4–5 years of hands-on software engineering experience in Python, with production-grade experience in ML model lifecycle • Fluent English 📩 𝗙𝗼𝗿 𝗰𝗼𝗻𝘁𝗮𝗰𝘁𝗶𝗻𝗴 https://t.me/Nadya_Shirshikova