AI Computing Software Development Engineer, TensorRT-LLM
Taipei
Workplace: OnsiteFull timeFunction: Data Science & Machine LearningExperience: 3+ yearsEducation: mastersSkills: ["Proactive","Independent","Communication","Team collaboration","Problem-solving"]Develop and optimize scalable LLM inference software for NVIDIA’s TensorRT-LLM team. You will analyze and improve LLM inference performance, implement kernels and runtime features for new models and algorithms, and stay current with academic and industrial advances. Collaborate across software, research, and product groups to shape deep learning inference architecture and hardware direction, while ensuring high-quality, high-performance implementation.
Loading
Loading job details...
Preparing the role view and application actions.

