Description
Cloudflare is hiring a Machine Learning Engineer to develop, optimize, benchmark, evaluate, and productionize machine learning models across its global serverless inference platform. The role focuses on low-latency, reliable, and efficient serving of frontier open LLMs, real-time voice models, and other customer-deployed models on heterogeneous GPUs and accelerators. Responsibilities include inference optimization, distributed infrastructure integration, deployment workflows, observability, regression testing, and mentoring engineers. The position is available in Austin, Texas, or London, United Kingdom, with a hybrid work arrangement.
