Summary
Yuanjing Shi is a GenAI ML research engineer with eight years of experience building and optimizing large-scale multimodal inference systems, currently contributing to Apple Intelligence on-device AI. Previously at NVIDIA and OctoAI he focused on accelerated LLM inference, TensorRT-LLM, PyTorch/TVM model compilation and performance engineering, and helped bring ML models from research to production. His background includes building unstructured data solutions at Snowflake and distributed database experience from an internship at Microsoft, giving him a strong systems-first approach to ML engineering. Trained at UIUC and The Hong Kong Polytechnic University, he blends deep model optimization expertise with practical deployment know-how and a knack for squeezing high performance out of constrained devices. An avid learner (his GitHub motto: "Learn to program"), he thrives on translating research advances into real-world, on-device ML capabilities.
8 years of coding experience
5 years of employment as a software developer
BSc (Hons) Computer Science, BSc (Hons) Computer Science at The Hong Kong Polytechnic University
Master of Science - MS Computer Science, Master of Science - MS Computer Science at University of Illinois Urbana-Champaign
Chinese, Chinese, English