Intel AI Workload Optimization Intern 

China, Shanghai 

942922292

Job Description:

Artificial Intelligence (AI) is transforming our lives and is everywhere. At INTEL, we are part of this AI revolution. Our software stack integrates seamlessly into customer frameworks, which are used by millions of end users. As our AI engineering team in Shanghai continues to grow, we are looking for a passionate graduate technical intern to help us deliver high-performance and high-quality deep learning solutions to our customers. Our team’s work includes:

• Optimizing performance for key use cases/models, debugging and resolving issues related to accuracy and memory management
• Designing and developing model deployment architectures, such as implementing new features on vLLM/SGLang to accelerate inference (e.g., P/D disaggregation)
• Developing and debugging high-performance kernels for INTEL accelerators
• Communicating with direct teammates, collaborators, and architects to discuss issues, propose solutions, provide status updates, and gather feedback
• Applying innovative ideas to enhance our products

Qualifications:

• Currently pursuing a Master’s or Ph.D. degree in Computer Science, Artificial Intelligence, Software Engineering, or a related field
• Strong programming skills in C++ and Python
• Solid understanding of deep learning fundamentals and hands-on experience
• Proficient in both written and spoken English
• Passionate about problem-solving and proactive thinking
• Nice to have:
  • Experience with LLMs or AIGC and a deep understanding of model architectures
  • Or experience with PyTorch, vLLM, or SGLang
  • Or experience in GPU kernel development
• Availability to work at least 3 days per week and commit to an internship duration of more than 6 months

Student / InternShift 1 (China)PRC, Shanghai

This role will require an on-site presence. * Job posting details (such as work model, location or time type) are subject to change.