A2 Labs is now
! Read more

Automatically unlock peak GPU performance

Mako writes, optimizes, and deploys GPU code that reduces costs, speeds up AI, and feels like magic

Try the live demo below to see Mako in action

running on

How It Works

Mako leverages an LLM agent to generate, validate, and inject custom GPU kernels into your PyTorch workloads, then serves them with SGlang or vLLM for blazing-fast inference.

Mako Kernel Agent

Generate GPU kernels that compile, are numerically correct, and run faster

Seamless PyTorch Integration

Automatically inject the kernel via torch.compile and deploy to SGlang or vLLM

Mako Optimization Platform

Auto-tune kernels and inference engine hyperparameters to maximize performance

Meet the Team

Over 30 years of experience bringing high performance AI from research into production.

Waleed Atallah Chief Executive Officer

Waleed Atallah

Chief Executive Officer

Lukasz Dudziak Chief Technology Officer

Lukasz Dudziak

Chief Technology Officer

Mohamed Abdelfattah, Ph.D Chief Science Officer

Mohamed Abdelfattah, Ph.D

Chief Science Officer

Angels and Advisors

Jeff Dean

Jeff Dean

Chief Scientist at Google

Micah Villmow

Micah Villmow

Fmr. Principal SWE at NVIDIA, TensorRT

David Levy

David Levy

Fmr. Startups at AWS

Abdel-rahman Mohamed

Abdel-rahman Mohamed

Head of AI at Rembrand

Nicholas Lane

Nicholas Lane

Prof. at Cambridge University and CSO at Flower

Ben Fielding

Ben Fielding

Co-founder and CEO at Gensyn

Recent Blogs

Working at MAKO

Shape the Future of AI with Us!

Join MAKO, where creativity meets cutting-edge innovation. Be part of a passionate team making breakthroughs in that shapes industries and changes lives.

Ready to make an impact?Explore Opportunities

Stay in Touch

Keep up with the latest on AI portability and performance.