
Preferred Networks is hiring a
MN-Core LLM Serving Engine Engineer
About Preferred Networks
Preferred Networks is an AI company based in Tokyo working across the stack, from AI chips and computing infrastructure to LLMs and products. You may already know us indirectly if you\'ve used software we\'ve built, such as Optuna or CuPy (or Chainer, back in the day). We are designing in-house chips (MN-Core series) and training LLMs (PLaMo series). Our team is actively hiring for two roles related to these endeavors.
Job Description
Role to build software infrastructure to serve LLMs using our MN-Core L1000 inference accelerator. Design and implement a high-performance serving stack, integrate with our in-house hardware, and collaborate with ML, systems, and software teams. This role requires relocation to Japan with visa and relocation support provided.Remote
Remote Conditions
Remote within Japan; relocation to Japan required; visa and relocation support provided.
Salary
Not Specified
Benefits
Visa and relocation support
Tech Tags
No tags
Date Listed
04 August, 2026 (about 16 hours ago)








