Luma AI is seeking a world-class engineer to help build foundational infrastructure for large-scale multimodal models in the UK. You will own end-to-end model serving, scheduling, and GPU fleet optimization to deliver high-throughput inference and reliable services.
You will design dynamic systems for hot-swapping models, own CI/CD pipelines, and develop APIs enabling product and research teams to ship innovative features at scale.
#J-18808-Ljbffr
