Middle MLOps Engineer

Role overview Deploy and operate machine-learning models in production across cloud environments and client-managed servers. You’ll work on model serving, GPU-backed infrastructure and the systems used to monitor models and data pipelines, carrying features through to production.

Responsibilities - Deploy and operate models in cloud and on-premise environments. - Configure model serving with vLLM, Triton or comparable tools. - Work with GPU-backed systems to support production workloads. - Use Docker, Kubernetes and CI/CD in deployment workflows. - Monitor models and data pipelines. - Own feature delivery from design through production.

Requirements - 2–4 years of commercial MLOps experience. - Experience with model serving tools such as vLLM or Triton, or similar systems. - Familiarity with GPUs and production model deployment. - Experience with Docker, Kubernetes and CI/CD. - Ability to monitor models and data pipelines. - Good written English; Russian or Uzbek is a plus.

Benefits and work setup - Remote-first work, with the option of a hybrid arrangement in Tashkent. - Work on AI assistants, private language-model and retrieval systems, and enterprise software. - Salary set in USD according to experience. - Join a small, experienced team and work directly with its leadership.