AI Framework Engineering

Intel Intel · Semiconductors · Shanghai, China

Intel CAIGC is seeking an AI Framework Engineer to advance AI technologies and software ecosystems, focusing on enabling the AI PC ecosystem and delivering full-stack GPU IP solutions. The role involves research, validation, performance evaluation, and optimization of AI models and frameworks on Intel platforms.

What you'd actually do

  1. AI Technology Research and Validation: Conduct research on emerging AI technologies (e.g., model quantization, graph structure transformation), and deploy and optimize proof-of-concept (PoC) projects on Intel platforms.
  2. Large Language Model (LLM) Performance Evaluation and Tool Development: Perform performance testing on the latest LLMs on Intel platforms and develop functional modules for testing tools.
  3. Performance Analysis and System Optimization: Analyze performance test results, identify software bottlenecks (e.g., operator latency, memory usage), and propose optimization strategies to improve inference speed and resource efficiency。

Skills

Required

  • Python
  • C++
  • PyTorch
  • OpenVINO
  • Hugging Face Transformers
  • vLLM
  • SGlang
  • artificial intelligence fundamentals
  • distributed systems
  • algorithms
  • profiling tools and techniques
  • optimize code for various hardware backends

Nice to have

  • Advanced problem-solving skills
  • complex computational and algorithmic challenges
  • Strong communication skills
  • driving innovation
  • transformative AI technologies

What the JD emphasized

  • deploy and optimize proof-of-concept (PoC) projects on Intel platforms
  • Perform performance testing on the latest LLMs on Intel platforms
  • Analyze performance test results
  • optimize code for various hardware backends

Other signals

  • AI PC ecosystem
  • full-stack GPU IP solutions
  • AI software ecosystem