Senior AI Inference Platform Architect
CoreWeave
CoreWeave is seeking an experienced Staff Software Engineer for the Inference team to lead architecture, performance, and reliability across multi-team services. You will shape cross-cutting design initiatives in request routing, scheduling, and GPU resource management, targeting strict P99 SLAs.
You will implement advanced optimizations like speculative decoding and KV-cache reuse while establishing benchmarking and observability practices across infrastructure boundaries.
#J-18808-LjbffrReference: WJ-766_21084838