Workload Optimization Intern

Intel

Shanghai, China
Onsite
C++ and python programming proficiency
Deep learning fundamentals knowledge
Master's or ph.d. student status
Intel is seeking a Graduate Technical Intern for its AI Engineering team in Shanghai, focusing on workload optimization and performance enhancement of deep learning solutions. The role requires strong programming skills and a solid understanding of deep learning fundamentals

Job Summary

  • The role focuses on optimizing key AI use cases and resolving issues related to accuracy and memory management.
  • Candidates will design model deployment frameworks leveraging new features in vLLM to accelerate inference.
  • The position requires developing high-performance kernels specifically for Intel GPU and CPU architectures.

Matching Summary

Match Score: 85

Intel is seeking a Graduate Technical Intern for its AI Engineering team in Shanghai, focusing on workload optimization and performance enhancement of deep learning solutions. The role requires strong programming skills and a solid understanding of deep learning fundamentals.

Skills & Requirements

Must-have

  • C++ and Python programming proficiency
  • Deep Learning fundamentals knowledge
  • Master's or Ph.D. student status

Nice-to-have

  • Experience with LLMs and Multimodal models
  • Familiarity with vLLM inference frameworks
  • Hands-on GPU Kernel development experience

Key Requirements

  • Current Master's or Ph.D. student in CS or related field
  • Minimum 4 days per week availability
  • Commitment of 6 months or longer

Work Rights

Not specified

Tailored Resume

Cover Letter