Description
CoreWeave is hiring a Senior Software Engineer, Inference to own critical technical designs and infrastructure areas for its Kubernetes-native inference platform serving generative AI and real-time inference workloads. The role focuses on request routing, adaptive scheduling, cost-per-token analytics, GPU resource isolation, micro-batch schedulers, speculative decoding, KV-cache reuse, capacity planning, autoscaling, and P99 SLA improvements. Candidates need a bachelor’s or master’s degree in computer science or a related field, at least three years of distributed-systems or high-performance cloud-services experience, Python or Go expertise, production Kubernetes experience, and knowledge of inference internals. The base salary is 321,000 PLN to 428,000 PLN gross annually, with medical, dental, pension, life assurance, and other benefits.
