Description
Cohere is seeking a Site Reliability Engineer to join their Model Serving team. The successful candidate will be responsible for building, deploying, and operating high-performance, scalable, and reliable machine learning systems, specifically focusing on optimizing NLP models for production environments. This role involves automating service management, ensuring observability and resilience, meeting Service Level Objectives (SLOs), collaborating with internal teams, and fostering team development. The ideal candidate will have extensive experience in large-scale production infrastructure, particularly with Kubernetes, distributed systems, and various cloud platforms.
