<aside> <img src="/icons/city_gray.svg" alt="/icons/city_gray.svg" width="40px" /> Mako, Inc.

</aside>

<aside> <img src="/icons/row_gray.svg" alt="/icons/row_gray.svg" width="40px" /> Table of Contents

</aside>

<aside> <img src="/icons/flash_gray.svg" alt="/icons/flash_gray.svg" width="40px" /> Apply Now!

</aside>

Summary

If you think you’re a generally exceptional person, we’d love to hear from you. Submit an application and highlight your key skills that will contribute to our success.

About Mako

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

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

Requirements

• Super smart
• Cool and chill
• Down to work hard

Nice to Have

• Experience training/fine-tuning LLMs for code generation
• Experience with CUDA/HIP/Triton/etc
• Experience with vLLM or SGlang or the like

To Apply

Fill out this form