Ai Frameworks Software Engineer – Model Compression Algorithm

Inteelabs

Shanghai, PRC
Intel neural compressor product development
Quantization and compression techniques
Llms and text-to-image/video models
Responsibilities include developing the Intel Neural Compressor product and related tools, optimizing for Intel AI platforms including CPU, GPU, and AI Accelerators

Job Summary

  • Responsibilities include developing the Intel Neural Compressor product and related tools, optimizing for Intel AI platforms including CPU, GPU, and AI Accelerators.
  • Research and implement quantization and compression techniques for large language models (LLMs) and text-to-image/video generation models.
  • Track and explore cutting-edge directions in efficient model deployment and inference/finetuning acceleration.

Matching Summary

Responsibilities include developing the Intel Neural Compressor product and related tools, optimizing for Intel AI platforms including CPU, GPU, and AI Accelerators.

Skills & Requirements

Must-have

  • Intel Neural Compressor product development
  • quantization and compression techniques
  • LLMs and text-to-image/video models
  • Python/C++ programming proficiency
  • deep learning framework fundamentals

Nice-to-have

  • strong self-motivation
  • problem-solving skills
  • passion for technological innovation
  • continuous exploration and improvement

Key Requirements

  • Master's or PhD degree in computer science or related subjects
  • Familiarity with model compression techniques
  • Strong teamwork and collaboration skills
  • Good English oral and written skills

Work Rights

Not specified

Tailored Resume

Cover Letter