MLOps Engineer

Firebird.ai is seeking a seasoned professional to manage the infrastructure supporting their production machine learning and large language model operations. The daily responsibilities involve overseeing the deployment, reliability, scalability, and observability of GPU-based AI services within Kubernetes environments. This position sits at the crossroads of machine learning, infrastructure, and platform engineering, focusing on creating systems that allow ML and product teams to deploy and run models effectively at scale. Collaboration with ML Engineering, Platform, and Infrastructure teams is central to the role, with specific goals including improving GPU utilization, automating deployment processes, and optimizing inference infrastructure. The objective is to ensure that production AI services maintain high levels of reliability and performance. The employer explicitly requires an experienced candidate for this position. The job description does not specify particular software tools or programming languages beyond the general mention of Kubernetes and GPU-based services. There are no stated language requirements for this role. The working arrangement is not detailed in the provided text, nor are there mentions of specific office locations beyond the general Yerevan context. This opportunity is suitable for engineers who possess significant experience in building and operating complex AI infrastructure and who thrive in collaborative, cross-functional team environments.