CoreWeave
Teams at CoreWeave
Recently posted jobs
Cloud • Information Technology • Machine Learning
Develop and run rigorous benchmarks and profiles for LLM inference workloads to identify bottlenecks and drive targeted performance optimizations across frameworks, runtimes, and GPU hardware. Design experiments (quantization, caching, speculative decoding), validate changes against real traces, partner with platform engineers to productionize improvements, and produce clear technical writeups to guide model-serving, runtime, and hardware decisions.
Cloud • Information Technology • Machine Learning
Lead and grow the engineering team productizing and operating an inference offering. Drive roadmap execution with Product, improve reliability, observability, release and incident processes, integrate platform capabilities, and deliver developer-friendly tooling and application-layer enhancements to scale production ML workloads.
Cloud • Information Technology • Machine Learning
Debug and fix complex kernel and container runtime interactions for a large GPU fleet: investigate kernel crashes, cgroup and namespace edge cases, and scheduler/memory issues; develop and upstream kernel or container-runtime patches; build observability tooling and partner with hardware, platform, and fleet teams during incident response.
