Senior MLops Engineer
Компания: [Название компании]
Зарплата: по договоренности
Тип занятости: #Офис
Локация: #Dubai
Позиция: #Senior
We are looking for a 🚀 Senior MLops Engineer with proven experience deploying and managing large-scale ML infrastructure for LLM, TTS, STT, Stable Diffusion, and other GPU-intensive models in production. The candidate will lead the design and operation of cost-effective, highly available, and high-performance serving stacks in an AWS environment powered by Kubernetes.
Обязанности
— Design and operate ML infrastructure for large-scale models (LLM, TTS, STT, Stable Diffusion)
— Optimize GPU-aware scaling for high-load deployments
— Lead cost-effective and high-performance serving stack development in AWS/Kubernetes
Требования
— 4+ years of Python software engineering with ML model lifecycle experience
— 2+ years with Triton, vLLM, Ray Serve, TorchServe, or similar
— Experience deploying and optimizing LLMs/LDMs (e.g., Stable Diffusion) under high load
— Fluent English
Что компания предлагает
— [Преимущество 1]
— [Преимущество 2]
— [Преимущество 3]
Контакт для связи:
TG: https://t.iss.one/Lek_Ol
LI: https://www.linkedin.com/in/olesia-lekontseva-415436238/
⚠️ Для удобства указывайте ссылку на вакансию
Ссылка: https://t.iss.one/it_match_devops/109
Стек технологий: #Python #AWS #Kubernetes #Triton #vLLM #RayServe #TorchServe #LLM #StableDiffusion
Компания: [Название компании]
Зарплата: по договоренности
Тип занятости: #Офис
Локация: #Dubai
Позиция: #Senior
We are looking for a 🚀 Senior MLops Engineer with proven experience deploying and managing large-scale ML infrastructure for LLM, TTS, STT, Stable Diffusion, and other GPU-intensive models in production. The candidate will lead the design and operation of cost-effective, highly available, and high-performance serving stacks in an AWS environment powered by Kubernetes.
Обязанности
— Design and operate ML infrastructure for large-scale models (LLM, TTS, STT, Stable Diffusion)
— Optimize GPU-aware scaling for high-load deployments
— Lead cost-effective and high-performance serving stack development in AWS/Kubernetes
Требования
— 4+ years of Python software engineering with ML model lifecycle experience
— 2+ years with Triton, vLLM, Ray Serve, TorchServe, or similar
— Experience deploying and optimizing LLMs/LDMs (e.g., Stable Diffusion) under high load
— Fluent English
Что компания предлагает
— [Преимущество 1]
— [Преимущество 2]
— [Преимущество 3]
Контакт для связи:
TG: https://t.iss.one/Lek_Ol
LI: https://www.linkedin.com/in/olesia-lekontseva-415436238/
⚠️ Для удобства указывайте ссылку на вакансию
Ссылка: https://t.iss.one/it_match_devops/109
Стек технологий: #Python #AWS #Kubernetes #Triton #vLLM #RayServe #TorchServe #LLM #StableDiffusion