MLOps Engineer, ML Platform and Delivery

Firebird.ai is seeking an experienced MLOps Engineer to manage the infrastructure for their machine learning and large language model workloads in Yerevan. The role involves deploying and ensuring the reliability and scalability of GPU-based AI services within Kubernetes environments. Daily tasks include building and enhancing Kubernetes infrastructure, designing deployment patterns for AI services, and managing CI/CD pipelines and infrastructure configurations. The engineer will also focus on observability using tools like Prometheus and Grafana, while optimizing GPU utilization and workload scheduling. Candidates should have a strong background in machine learning infrastructure and experience with tools such as Kafka, Redis, ClickHouse, and PostgreSQL. The position is permanent and requires collaboration with various teams, making it suitable for individuals who thrive in a cross-functional environment. The role is office-based, emphasizing hands-on involvement in production systems and incident response.