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

Makora is a venture-backed AI infrastructure company building the optimization software and inference platform that make frontier AI models run faster, cheaper, and more efficiently across any hardware. There are three 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
3. MakoraInference uses Generate and Optimize to deliver frontier open-source models as ultra-fast inference endpoints.

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