Software Engineer, Inference AI/ML

Join the Inference team at CoreWeave to ship production features that improve latency, reliability, and cost for model serving on our GPU platform. As an IC1, you will implement well-scoped changes in Python/Go/C++, write tests and design docs, add metrics and dashboards, and learn incident response in a guided on-call rotation. You will contribute to performance experiments with guidance.

Requires BS/MS in CS, EE, or equivalent experience; foundational knowledge of data structures, algorithms, and networked services; experience with Python or Go, Linux, Git/CI; exposure to containers and Kubernetes; curiosity about GPU inference concepts. Preferred: internship deploying microservice/ML inference, coursework with PyTorch/TensorFlow, CUDA projects, familiarity with Grafana/Prometheus/OpenTelemetry.