jobs

Site Reliability Engineer, Inference Infrastructure

Who are we?Cohere is the leading security-first enterprise AI company. We build cutting-edge foundation AI models and end-to-end products that are designed to solve real-world business problems.We’re training and deploying frontier models f

Company

Cohere

Location

Toronto; San Francisco; New York; Montreal

Status

Open

Posted

2026-01-12T23:00:51.072+00:00

Cohere is hiring a site reliability engineer for its Model Serving team, which runs the platform serving the company's large language models through API endpoints. The work covers automated deployment and operations, custom Kubernetes operators for language model deployments, observability, resilience, SLOs and an on-call rotation, plus some customer-specific deployments. The posting asks for 5+ years of production infrastructure experience, Kubernetes and GPU workloads, multi-cloud and Linux experience, and Golang or C++. The role is listed as remote, with offices in several cities.