Ai Frameworks Software Engineer – Model Compression Algorithm

Intel Retiree Medical Plan Trust

Shanghai, PRC
Master's or phd in computer science
Deep learning framework proficiency
Quantization and pruning techniques
The role involves developing the Intel Neural Compressor product and related auto-round tools

Job Summary

  • The role involves developing the Intel Neural Compressor product and related auto-round tools.
  • Candidates will research and implement quantization techniques specifically for large language models and generative AI.
  • The position requires strong collaboration skills and a drive for continuous engineering improvement within a team environment.

Matching Summary

The role involves developing the Intel Neural Compressor product and related auto-round tools.

Skills & Requirements

Must-have

  • Master's or PhD in Computer Science
  • Deep learning framework proficiency
  • Quantization and pruning techniques
  • Python and C++ programming skills

Nice-to-have

  • Experience with LLM fine-tuning
  • Inference optimization background
  • Self-motivated problem solver
  • Passion for technological innovation

Key Requirements

  • Master's or PhD degree required
  • Major in computer science or related field
  • On-site presence required in Shanghai

Work Rights

Not specified

Tailored Resume

Cover Letter