NVIDIA is focusing on the advancement of large language models and their applications in agentic use cases. The role involves researching and developing new inference algorithms and protocols to enhance algorithmic performance and efficiency. Engineers will conduct workload analysis to optimize the performance of complex inquiry systems. Collaboration with various teams will also be essential to refine NVIDIA solutions for sophisticated tasks.
Location: Santa Clara, CA
Posted: Aug. 20, 2024, 8:31 a.m.
Apply Now Company Website