NVIDIA in Santa Clara is seeking outstanding AI systems engineers to develop groundbreaking inference systems software, libraries, and GPU kernel technologies for NVIDIA hardware. You will build new abstractions and runtimes for high-impact AI workloads and collaborate with NVIDIA teams across DL frameworks and GPU architectures.
You will contribute to open source communities like FlashInfer, vLLM, and SGLang while delivering efficient acceleration for LLMs and agents.
#J-18808-Ljbffr