AI Frameworks Engineer – GPU Performance for Generative AI (OpenVINO)

TL;DR

AI Frameworks Engineer (OpenVINO): Building and optimizing generative AI workloads on hirify.global GPUs with an accent on HW-aware software and performance optimization. Focus on identifying and resolving compute, memory, and bandwidth bottlenecks for LLMs and diffusion models to maximize GPU architectural efficiency.

Location: Hybrid in Seoul, South Korea

Company

hirify.global is a global leader in semiconductor design and software, driving AI innovation through its foundational software stacks and hardware IP.

What you will do

• Take technical ownership of performance-critical paths for generative AI workloads (LLMs, diffusion models) on hirify.global GPUs.
• Analyze end-to-end execution of AI models to identify compute, memory, bandwidth, and parallelism bottlenecks.
• Implement and optimize generative AI techniques, adapting state-of-the-art ideas to hirify.global GPU architectures.
• Translate deep understanding of GPU hardware architecture into efficient, scalable, and maintainable software designs.
• Diagnose and resolve complex issues spanning runtime, kernel, driver, and hardware boundaries.
• Collaborate with global teams across software, hardware architecture, and validation.

Requirements

• Degree in Computer Science, Computer Engineering, or a related field.
• 3+ years of professional software engineering experience.
• Strong programming skills in C and C++, with working experience in Python.
• Experience working with large and complex C++ codebases with a focus on performance and maintainability.
• Proven analytical thinking and strong problem-solving abilities for ambiguous technical challenges.

Nice to have

• Experience with GPU programming or parallel computing, such as multi-threading, SIMD, or accelerator programming models.
• Strong understanding of computer and GPU architecture and its impact on software performance.
• Technical understanding of generative AI models from a system and performance perspective.
• Familiarity with AI runtimes or frameworks.

Culture & Benefits

• Structured hybrid work model combining remote work and in-office collaboration.
• Opportunity to work on state-of-the-art AI models pushing the limits of GPU performance.
• Participation in a global software team delivering core IP for AI PCs and data centers.