Staff Software Engineer - Serverless

Build the core systems behind Runware’s serverless platform, including workload execution, routing, scheduling, isolation and scaling leveraging our inference engine

Make it simple for developers to deploy models and run AI workloads without managing GPUs, servers, queues or infrastructure through a simple SDK interface

Design and improve the control plane for serverless execution, including APIs, workers, lifecycle management, retries and failure handling

Work closely with our infrastructure and ML teams to improve workload startup time, GPU utilisation, model warm-up, caching and placement

Build observability that makes serverless workloads easy to monitor, debug and operate at scale globally

Lead the technical design, mentor other engineers and help define the engineering standards for a new product area