Description
Intel is hiring an on-site On-Device AI Engineer in Shanghai to collaborate with model teams on deploying LLMs, VLMs, image and video generation models, and AI agents to end devices. The role involves rapid prototyping, inference pipelines, media codecs, automation tooling, system integration, performance tuning, and hardware-software co-optimization across CPUs, GPUs, and NPUs. Candidates should have a master's or PhD, proficiency in Python or C/C++, and familiarity with Windows or Linux; experience with AI applications, inference frameworks, model optimization, and GPU/NPU acceleration is preferred.
