NVIDIA is seeking an engineer to accelerate API integration across the CUDA-X math library stack for LLM and agentic AI workflows. You will ensure high-performance applications via CUDA-X libraries, collaborating with stakeholders to deliver LLM-enhanced releases and build tooling to measure AI-generated code quality.
The role emphasizes API design, documentation, and scalable, explainable tooling, with a focus on LLM-first representations and cross-tool compatibilities.
#J-18808-LjbffrLLM-First Math Libraries Engineer & Developer Experience in new york at Unknown Company
This position is listed as full time and onsite.