About us

Mako is a venture-backed tech startup building software infrastructure for high performance AI inference and training on any hardware. There are two core components:

  1. MakoOptimize automatically selects and swaps GPU kernels in combination with tuning inference engine (vLLM, SGlang, etc..) hyperparameters to optimize performance
  2. MakoGenerate writes GPU kernels in CUDA, HIP, and Triton using LLMs

We are located in New York City and GdaƄsk.

Currently open job positions


General Application

AI Engineer

Founding Technical Product Manager

Enterprise Sales Leader

AI Engineer Intern

To Apply

Fill out this form