Description
NVIDIA is hiring a System Software Engineer - Agentic Retrieval to develop and optimize Rust-based data processing frameworks and GPU-accelerated pipelines for indexing, querying, deduplicating, filtering, and classifying multimodal datasets used in LLM and agentic retrieval systems. The role involves benchmarking and optimizing algorithms in Python, collaborating with LLM and ML researchers, building production tools and libraries, maintaining continuous delivery, and evaluating AI models and frameworks. Candidates need a bachelor’s or master’s degree in a relevant field, at least six years of experience, cloud and MLOps knowledge, and expertise in NLP, LLM, VLM, generative AI, and agentic retrieval workflows.
