Skip to content
Back to jobs

Posted 1 month ago

Preferred Networks

LLM Inference Optimization Engineer

Roles

Compensation

Visa and relocation support provided.

Tech stack

Location

Tokyo, Japan, Remote in Japan

Work setup

Full-time Employee
Senior

Description

Preferred Networks is an AI company based in Tokyo working across the stack. They design in-house chips (MN-Core series) and train LLMs (PLaMo series). They are hiring two roles: (1) MN-Core LLM Serving Engine Engineer to build software infrastructure to serve LLMs using the upcoming inference accelerator MN-Core L1000. (2) LLM Inference Optimization Engineer to improve the inference engine powering their API service and maintain PLaMo implementations in open source projects such as vLLM. Both roles require relocation to Japan, and the company provides visa and relocation support.

Similar jobs

  • Loading similar jobs...