ABOUT KOG
At Kog, we're building real-time LLM inference for AI agents.
Coding agents execute sequences of tasks where each step depends on the model's previous response. The faster the model generates tokens, the faster these agents can reason, code, and act.
Our approach is to co-design model architecture, the inference engine, and low-level GPU kernels to minimize generation latency on standard NVIDIA and AMD datacenter GPUs.
We've developed several technologies to make this possible:
- Monokernel: a persistent GPU program that keeps the entire token generation loop on the GPU, avoiding CPU handoffs.
- KCCL: our custom inter-GPU communication layer, designed to minimize latency.
- Delayed Tensor Parallelism (DTP): a model architecture that overlaps communication with computation and weight loading.
- Laneformer 2B: our code-generation model demonstrating this co-design approach.
Our engineers work directly with GPU hardware, using CUDA, PTX, HIP, and CDNA ISA to optimize execution.
Implementing and optimizing a new AI model for a specific GPU architecture can take months of manual engineering. Meanwhile, new models are constantly being released.
Our goal is to use AI agents to implement and optimize the models we choose on the GPUs we choose, in a fraction of the time required today.
These agents will build on the GPU optimizations and hardware insights our team has developed. They'll explore optimization strategies, generate and modify kernels, verify correctness, benchmark performance on real hardware, and iterate based on the results.
We want to make model porting and GPU optimization much faster and repeatable, allowing Kog to keep pace with the latest AI models rather than spending months adapting each one manually.
This is a major engineering direction we're now developing, and you'll help shape it.
Learn more at https://blog.kog.ai.
WHAT YOU'LL WORK ON
You'll join our GPU engineering team to tackle challenging performance problems and help build the internal agents that will accelerate this work.
- Develop and optimize GPU kernels using C++, CUDA, HIP, and low-level instructions.
- Investigate GPU architecture, memory access, synchronization, and execution bottlenecks.
- Profile and benchmark workloads to identify and validate performance improvements.
- Optimize inference operations and communication across multiple GPUs.
- Implement and optimize new AI models on NVIDIA and AMD GPUs.
- Help build AI agents for GPU engineering, enabling automated code optimization, correctness testing, benchmarking, and iterative improvements.
- Take ownership of technical decisions and their implementation.
WHAT WE'RE LOOKING FOR
We're looking for an experienced GPU Engineer who can contribute quickly and independently to complex performance problems.
- Strong hands-on experience developing and optimizing GPU kernels, ideally using CUDA C++ or HIP/ROCm.
- Deep understanding of GPU architecture, memory hierarchy, parallel execution, and performance bottlenecks.
- Strong C++ skills and experience profiling and benchmarking GPU workloads.
- Proven ownership of challenging technical projects, from implementation to measured results.
- Interest in developing AI agents and tools to accelerate GPU engineering.
Experience with PTX, CDNA ISA, multi-GPU systems, low-latency inference, or GPU performance portability is particularly valuable.
A PhD in HPC, computer science, or a related field is a plus when backed by substantial engineering work. Previous experience building AI agents is not required.
LOCATION AND AVAILABILITY
Candidates must already be based in Paris or elsewhere in Île-de-France.
We are not considering relocation from other regions or countries for this position.
We're looking for someone who can join the team quickly.