Inference Systems Performance Architect

You will be the architect for end-to-end inference performance: how a request moves through tokenization, prefill, decode, and the fabric between them, and how a deployment is sized against customer SLOs. The work has two coupled pillars. One is reproducible workload capture and benchmarking, building replayable representations of real and increasingly agentic traffic so measurements reflect production rather than a…

SambaNova has 75 open roles right now, 4 of them remote. Most are in Engineering, Marketing & Community and Operations. The median advertised salary across its roles with a published range is $218K. See all its roles