AI Framework Vllm Optimization Intern

Intel Intel · Semiconductors · Shanghai, China

AI Software Engineering Intern focused on designing, developing, and optimizing AI software solutions, including algorithms, frameworks, and architectures. Key responsibilities include tuning deep learning models, exploring model compression techniques (quantization, pruning), and conducting applied research for system-level deployment and hardware integration. The role emphasizes practical engineering applications and inference optimization.

What you'd actually do

  1. Design, develop, and optimize AI software solutions, including algorithms, frameworks, and architectures.
  2. Assist in tuning and implementing deep learning models for enhanced accuracy and performance.
  3. Explore model compression techniques, such as quantization and pruning, to improve system efficiency.
  4. Collaborate with internal teams and external partners to create innovative AI solutions tailored for system-level deployment.
  5. Conduct applied research to advance AI methodologies and their integration with hardware solutions.

Skills

Required

  • deep learning fundamentals
  • large language model applications
  • model compression techniques
  • quantization
  • pruning
  • Python

Nice to have

  • fine-tuning
  • inference optimization
  • agent development

What the JD emphasized

  • optimize AI software solutions
  • model compression techniques
  • inference optimization

Other signals

  • optimize AI software solutions
  • implement and tune models
  • model compression techniques
  • inference optimization