AI Computing Software Development Engineer, LLM Inference
NVIDIA
Shanghai, Beijing
Workplace: OnsiteFull timeFunction: Data Science & Machine LearningExperience: 2+ yearsEducation: mastersSkills: ["C++","C","TensorFlow","PyTorch"]Develop and optimize scalable inferencing software for TensorRT LLM and TensorRT Edge LLM, contributing to performance-tuned solutions across multiple platforms. Collaborate with software, research and product teams, stay ahead of AI/LLM advances, and publish findings at conferences to push the boundaries of GPU-accelerated AI runtimes.
