jobs

Lead Member of Technical Staff, 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

San Francisco; United States; New York; Toronto; Montreal

Status

Open

Posted

2026-04-28T09:48:38.89+00:00

Cohere's Model Serving team is hiring a Lead Member of Technical Staff for inference infrastructure. The role sets technical direction and architecture for deploying optimized NLP models to production, running the API endpoints that serve Cohere's large language models with low latency, high throughput and high availability. It also involves leading custom deployments for customers and mentoring engineers. The posting asks for 8+ years running production infrastructure at scale, deep Kubernetes and GPU-workload expertise, multi-cloud and Linux experience, compute cost management, and proficiency in Golang or C++. Technical leadership across teams and direct customer-facing design work are distinctive.