Jobs

Multiverse Computing is seeking a Senior MLOps Engineer to lead the technical vision for their Training and Inference Optimization team. This high-impact role involves architecting infrastructure for next-generation AI models, bridging systems programming and machine learning. The successful candidate will optimize large-scale LLM training using NVIDIA NeMo and build ultra-high-throughput serving systems with vLLM, TensorRT-LLM, and SGLang. The mission is to ensure models are state-of-the-art, production-hardened, cost-efficient, and performant at scale, requiring 5+ years of MLOps experience with a focus on LLM infrastructure.