Multiverse Computing in San Sebastian, Spain, seeks a Senior MLOps Engineer to lead the Training and Inference Optimization effort for next-generation AI models. You will architect scalable infrastructure powering NeMo-based training and ultra-high-throughput serving with vLLM, TensorRT-LLM, and SGLang.The role bridges systems programming and ML, optimizing large-scale training, tuning performance, and guiding cost governance.#J-18808-Ljbffr