3 days ago
Shanghai, ChinaIntern
Responsibilities
- Collaborate with model teams to drive on-device deployment of LLMs, VLMs, image/video generation models, and AI Agents.
- Rapidly prototype ideas and develop inference pipelines, media codecs, and automation tooling using Python or C/C++.
- Participate in technical evaluation, prototyping, system integration, performance tuning, and product iteration.
- Conduct hardware-software co-optimization for CPUs, GPUs, and NPUs.
- Work with model, hardware, and ecosystem stakeholders to scale cross-domain on-device AI solutions.
Requirements
- Master's or PhD degree is required, with exceptional bachelor's candidates also welcome; all majors are considered.
- Proficiency in Python or C/C++ and familiarity with Windows or Linux development environments.
- Curiosity about cutting-edge AI research, self-motivation, problem-solving ability, and the ability to turn prototypes into production-ready deliverables.
- Strong cross-team communication and collaboration skills.
- Prior personal projects, AI practice, or open-source contributions are preferred.
- Preferred experience includes LLM/VLM/AI Agent applications, RAG, tool-use workflows, PyTorch, OpenVINO, ONNX Runtime, model quantization, distillation, LoRA fine-tuning, on-device deployment, GPU/NPU acceleration, media processing, video codecs, and system performance optimization.
- Familiarity with AI coding tools such as Cursor and GitHub Copilot is preferred.
Benefits
- Student/intern role with an on-site work model in Shanghai, China.
- End-to-end exposure to models, agents, system software, media processing, and hardware acceleration.
- Full-cycle project ownership from initial prototyping through product launch.
- Mentorship from experienced mentors and personalized career development.
- Access to Intel's global R&D network and leading model teams.
About Intel
Intel is a public semiconductor company that designs and manufactures CPUs and other silicon for PCs, servers, networking, edge, and embedded systems, and also offers foundry services plus AI and graphics accelerators. Founded in 1968 and headquartered in Santa Clara, it sells primarily to OEMs, cloud providers, and device makers worldwide. Its portfolio includes x86 processors (Core and Xeon), Ethernet and chipset products, and the Mobileye autonomous driving platform.