Cadence Jobs

Together AI

We are seeking a software engineer to develop a Kubernetes-native control plane for provisioning and managing our GPU inference fleet. This role involves designing a manifest-driven API that allows the inference team to declare their needs, such as clusters, model deployments, or capacity adjustments. Our controllers will handle the underlying reconciliation, provider/runtime selection, and lifecycle management, abstracting away the complexities of the serving stack, scheduler, or hardware pool. You will also build systems to ensure fleet efficiency, including defragmentation, rebalancing logic for consolidating workloads, and scheduling/bin-packing improvements to maximize GPU utilization without compromising latency. The core objective is to decouple platform users from operational complexities while optimizing hardware capacity. This includes developing controllers, reconciliation loops, and self-service interfaces (API/CLI) for seamless operation, alongside event-driven systems for health monitoring, remediation, and utilization management, all designed to operate without human intervention. A product-oriented mindset is crucial, with a focus on building internal platforms and APIs that enhance the developer experience for consuming engineering teams. This role operates under a "you build it, you own it" philosophy, encompassing both software delivery and production support.

$160k - $280k