AI Software Development Engineer
Intel, PRC, Shanghai
What you will do
Collaborate with top domestic model teams to drive the on-device deployment of LLMs, VLMs, image/video generation models and AI Agents
Rapidly prototype innovative ideas; develop inference pipelines, media codecs and automation tooling using Python / C/C++
Participate in the full lifecycle including technical evaluation, prototyping, system integration, performance tuning and product iteration
Conduct system-level hardware-software co-optimization targeting CPUs, GPUs and NPUs; explore new approaches to boost engineering efficiency powered by AI
Align with model, hardware and ecosystem stakeholders to scale cross-domain on-device AI solutions
Nice to have
Hands-on experience building LLM/VLM/AI Agent applications, RAG and tool-use workflows
Familiarity with inference frameworks including PyTorch, OpenVINO and ONNX Runtime
Practical experience in model quantization, distillation, LoRA fine-tuning and on-device deployment