MLOps Engineer

Firebird.ai is seeking a skilled MLOps Engineer to manage the infrastructure supporting their machine learning and large language model workloads. The role involves overseeing the deployment, reliability, scalability, and monitoring of GPU-based AI services within Kubernetes environments. Daily tasks will include collaborating with machine learning, platform, and infrastructure teams to enhance GPU utilization, automate deployment processes, and optimize the infrastructure for inference. The position requires experience in building systems that facilitate the reliable deployment and operation of machine learning models at scale. While the advert does not specify particular qualifications, it implies that a strong background in MLOps and related technologies is essential. The job is based in Yerevan and is a full-time position. This role is ideal for individuals who thrive at the intersection of machine learning and infrastructure engineering, and who are eager to contribute to the performance and reliability of production AI services.