About us

Makora is a venture-backed AI lab building building tools to automate algorithm discovery and GPU performance engineering. There are two core components:

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

We are located in New York City and Gdańsk.

Currently open job positions

General Application

GPU Kernel Engineer

AI Engineer

AI Engineer Intern

Forward Deployed Engineer

To Apply fill out the form below

Fill out this form