jobs

Staff Software Engineer, Inference

CoreWeave is The Essential Cloud for AI™. Built for pioneers by pioneers, CoreWeave delivers a platform of technology, tools, and teams that enables innovators to build and scale AI with confidence. Trusted by leading AI labs, startups, and

Company

CoreWeave

Location

London, England

Status

Open

Posted

2026-08-05T19:18:07+00:00

CoreWeave's Inference team runs the Kubernetes-native platform behind large-scale GPU workloads. This staff-level role leads cross-team architecture for request routing, scheduling and GPU resource management, with P99 latency and cost-per-token as targets; the engineer also builds inference optimisations such as speculative decoding and KV-cache reuse and sets benchmarking and observability practice. The posting wants eight or more years on distributed systems, production Kubernetes depth, Go, Python or C++, and hands-on inference experience; open-source work on serving frameworks and CUDA-level GPU tuning are preferred.