KOG:

Kog is a real-time AI startup, created a little over a year ago, which aims to revolutionize how AI is used in digital experiences. The goal is to make AI faster, more efficient, and more intuitive.

We creatively optimize at a very low level with our own solutions and seek out new ideas that we implement ambitiously.

Kog is based on two axes:

• Hardcore GPU Engineering

• Custom model architectures for speed

Our final objective is to be 10x faster on GPUs and 10x faster on model architecture, thus 100x faster total!

We've built an inference engine optimized at the Assembly level, bypassing the inefficient abstraction layers, and we've made significant advancements in several areas:

• Inter-GPU communication

• Kernel fusion

• Grid synchronization

• Memory access optimization

The inference engine offers speed improvements 3 to 10 times greater compared to the best GPU alternatives, starting with AMD MI300X.

What you'll do:

We wish to strengthen our world-class team with technically brilliant individuals who want to take on this challenge. Your missions will include:

• Implementing cutting-edge AI models in low-level C++ code and Assembly on high-end AMD and NVIDIA GPUs

• Reverse-engineering subtle GPU features (such as memory page mappings, memory channels, hash functions, cache behaviors, credit assignment logic, etc.)

• Leveraging this knowledge to find and implement creative optimization ideas

• Optimizing the Kog inference engine to make AI inference incredibly fast (10x compared to vLLM, SGLang, or TensorRT-LLM—we are already at 3x!)

Who we'd like to work with :

• World-class talents with 5+ years of experience

• Proficiency in CUDA or ROCm

• Start-up mindset

• Team player attitude

• PhD or Top Engineering Schools

• Someone who has side projects or shows great passion and interest

What we offer:

• Competitive salary

• Equities (BSPCE)

• Elite technical challenges

• World-class team (9 engineers, including 3 PhD)

• A creative environment where your goal is to push back the limits

• Equipment you'll need to perform

• WeWork offices in the 13th district of Paris (near Station F)

• Afterworks during our Paris week

You can apply right below if you feel that you're up to the task!