DeepX

Generative AI Engineer

Seoul, South Korea

Recently posted

Apply on DeepX's career page

What you'd do

Analyze and profile state-of-the-art generative AI models focusing on edge inference.
Integrate AI inference frameworks (PyTorch,vLLM,Llama.cpp,ExecuTorch) on DEEPX NPUs.
Optimize generative AI model architectures using deep learning compiler technologies.

What they want

Deep understanding of generative AI model architectures (LLM,VLM,VLA) and inference pipelines.
Practical experience with modern AI frameworks and execution environments.
Solid understanding of AI compilers (LLVM,MLIR) and hardware translation processes.

Nice to have

Master's or Ph.D. in Computer Science,Machine Learning,or related fields.
Hands-on experience developing or optimizing pre-training/inference engines for LLMs.
Deep expertise in AI compiler infrastructures (LLVM,MLIR) or custom graph compilers.

Seoulstart's read

Visa tier (likely): E-7 specialty / professional (likely)
Korean language: Korean not required
English friendliness: High: JD in English, foreign-friendly signals
Context: Series D deep-tech startup with strong pre-IPO momentum; core engineering role conducted in English but stock options and Korean employment benefits signal Korean subsidiary structure; visa sponsorship likely straightforward for specialized AI talent.

This is Seoulstart's analysis of the public job description, not the employer's stated policy. Verify visa sponsorship, language requirements, and remote allowances directly with the recruiter.

View the full posting and apply on DeepX's career page

Related Seoulstart guides

Similar roles on Seoulstart

Browse all English-friendly jobs in Korea

Korea jobs hiring English speakers