The SRE will manage the scaling of a geographically distributed GPU inference network and oversee the lifecycle of new sites from provisioning to production. They are also responsible for maintaining network reliability, optimizing global routing, and building automation for observability and failure recovery.
You will own the end-to-end product console, including interface design, API development, and production maintenance. You will also set technical direction, mentor engineers, and collaborate with the infrastructure team to ensure a high-quality customer experience.
You will own the end-to-end customer journey and product strategy, working directly with the CTO to define what features to build. You will conduct customer research, analyze feedback, and translate technical requirements into actionable product plans.
You will build, operate, and scale backend services and GPU infrastructure within a distributed inference network. This role involves managing cloud services, ensuring system reliability, and participating in on-call rotations to maintain production environments.
