Remote job
Middle MLOps-инженер
Job details
About this role
Role overview Deploy and operate machine learning models in production, both in cloud environments and on customer-managed servers. You’ll help keep model serving and data pipelines running reliably, taking work from design through production operations.
Responsibilities - Deploy and maintain models in cloud environments and on customer infrastructure. - Set up model serving with tools such as vLLM, Triton, or comparable systems. - Work with GPU-backed deployments and supporting infrastructure. - Build and maintain containerized workflows and CI/CD processes. - Monitor models and data pipelines in production. - Own tasks from design through deployment and ongoing operation.
Requirements - 2–4 years of professional MLOps experience. - Experience serving models and working with GPUs. - Docker and Kubernetes skills. - Familiarity with CI/CD and production monitoring for models or data pipelines. - Ability to independently take work from design to production. - Good written English; Russian or Uzbek is an advantage.
Benefits and work setup - Remote-first work, with the option to work from anywhere or hybrid from an office in Tashkent. - Work on AI and enterprise systems for customers in Uzbekistan, South Korea, and the UAE. - Compensation in USD, based on experience and market level. - Direct collaboration with the CEO and a small senior team.