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

We are located in New York City and Gdańsk.

Currently open job positions

AI Engineer Intern

General Application

To Apply

Fill out this form