Description
NVIDIA is hiring a Senior AI Model Evaluation Engineer to design and operate decision-grade evaluation environments and pipelines for frontier LLMs, RAG, agents, vision models, and other multimodal systems. The role involves developing novel evaluation methodologies, building reproducible benchmark and regression infrastructure, analyzing large-scale results, and translating accuracy signals into release and research decisions. Candidates need a relevant advanced degree, at least six years of hands-on LLM or multimodal evaluation experience, strong statistical and experimental-design skills, and experience with evaluation infrastructure, HPC clusters, and large-scale workloads.
