DOUBLE SHIP: MakoGenerate now supports AMD MI300X GPUs! You can now generate #Triton #kernels for AMD MI300X for free on our website using the community version of MakoGenerate And you will be able to use OpenAI GPT5 to generate the code by the end of today. Check it out!

We're live with the Tenstorrent loud box GENERATE ALL KERNELS

Working with the best in the business 🫡

Watch our CEO on The Information's TITV 👇

Oh and we raised $8.5M from M13, Neo, Flybridge, Jeff Dean and more Join us to work on the hardest problems in code generation. Instant interviews for those with: - kernel writing experience (CUDA, Triton, HIP) - reinforcement learning (esp large scale) - good vibes

It’s been a privilege to learn from and partner with the brilliant team at Mako, an AI-powered platform for GPU kernel generation and optimization. AI at AMD sees an exciting opportunity here to unlock new levels of performance and developer productivity across the AI

Pictured: our CTO hard at work

MakoGenerate is coming to Anthropic's Claude Code soon

.Mako, a #startup co-founded by assistant professor Mohamed Abdelfattah, has raised $8.5 million in seed funding to tackle one of #AI’s most pressing infrastructure challenges: optimizing the efficiency of GPUs. Read more about the company: tech.cornell.edu/news/mako/ Cornell Engineering

See you in the city 😎🌉

Mako is hiring GPU kernel engineers. If you know how to write #CUDA, #Triton, or #HIP, apply and help us solve some of the hardest problems in code generation. We have the tools. We have the means. Algorithm discovery and development will never be the same. Join Mako!

We will see you next week!