Head of Inference

About the Role: The Company is seeking a Head of Inference to take ownership of model serving at a production scale for its AI infrastructure. This role is pivotal in the transition of the inference business into a standalone line, with a focus on lifting the inference platform from a beta stage to a generally available product with defined cost and latency SLAs. The successful candidate will be responsible for the end-to-end remit, including the serving stack, customer SLOs, and the underlying unit economics. The Head of Inference will also be tasked with pricing the platform, shaping the product roadmap, and driving the inference revenue line as it becomes a significant part of the company's business. Applicants for the Head of Inference position should be current or recent leaders of an inference platform program at a peer infrastructure provider, frontier lab, or hyperscaler. The role requires a dual focus, being both customer-facing on integration and SLAs, and platform-facing on serving and optimization. The ideal candidate will have a strong engineering background with the ability to translate technical expertise into economic terms, as they will be the key decision-maker for inference unit economics. The role involves direct line management of a team of platform engineers and SREs, with plans to expand the team, and therefore, leadership and hiring experience is essential. The Head of Inference will play a critical role in the company's growth, as inference is expected to become a major and profitable line of business. Hiring Manager TitleVP Platform FunctionsEngineeringProduct Management