Ai Frameworks Engineer – Gpu Performance For Generative Ai (openvino)

Intel

Seoul, South Korea
Hybrid
3+ years professional software engineering experience
Strong c and c++ programming skills
Experience with large complex c++ codebases
Intel is seeking an experienced AI Frameworks Engineer to optimize generative AI workloads on Intel GPUs as part of their OpenVINO team in Seoul, South Korea. The role requires strong programming skills, particularly in C and C++, along with a deep understanding of GPU architecture and performance optimization

Job Summary

  • This role focuses on driving the implementation and performance optimization of generative AI workloads on Intel GPUs as part of the OpenVINO team.
  • You will take technical ownership of performance-critical paths for models like LLMs and diffusion models, analyzing end-to-end execution to identify bottlenecks.
  • The position requires translating deep understanding of GPU hardware architecture into efficient, scalable, and maintainable software designs.

Matching Summary

Match Score: 85

Intel is seeking an experienced AI Frameworks Engineer to optimize generative AI workloads on Intel GPUs as part of their OpenVINO team in Seoul, South Korea. The role requires strong programming skills, particularly in C and C++, along with a deep understanding of GPU architecture and performance optimization.

Skills & Requirements

Must-have

  • 3+ years professional software engineering experience
  • Strong C and C++ programming skills
  • Experience with large complex C++ codebases

Nice-to-have

  • GPU programming and parallel computing experience
  • Understanding of computer and GPU architecture
  • Familiarity with AI runtimes or frameworks

Key Requirements

  • Computer science or related field degree
  • 3+ years of professional software engineering experience
  • Strong analytical thinking and problem-solving abilities

Work Rights

Not specified

Tailored Resume

Cover Letter