About this role
Kog builds the fastest LLM inference engine on standard datacenter GPUs.
Our Kog Inference Engine generates 3,000 output tokens per second per request on a single 8× AMD MI300X node and 2,100 on an 8× NVIDIA H200 node (FP16, batch size 1, no speculative decoding).
We are a team of 11 people, including 10 engineers and 4 PhDs.
Test it at playground.kog.ai http://playground.kog.ai. Read the technical details on the Kog Labs blog.
The hot path is a monokernel implemented with handwritten CUDA (with PTX inline assembly) on NVIDIA, and HIP (with CDNA ISA inline assembly) on AMD.
We optimize at the low level with engine/kernel/model co-design, using reverse engineering to understand and exploit the details of how the GPU hardware works at the micro level.
WHAT YOU WILL WORK ON
You will own the technical execution of the Kog inference engine at the hardware boundary. You write code, review kernels, define performance priorities, make architecture calls, and drive a small team toward improvements that matter in production.
You move between microscopic detail and system-level judgment with the same rigor.
- Own the monokernel pipeline, the single persistent GPU program that covers the full decode pass from QKV projection to LM head sampling, across AMD and NVIDIA architectures.
- Drive low-level GPU optimization, including impossibly-fast grid synchronizations and inter-GPU collectives, and optimized GEMM and attention kernels for specific batch sizes and context lengths.
- Build and maintain profiling infrastructure inside a monokernel, including custom instrumentation, device-timestamp frameworks, and per-stage analysis to translate machine behavior into concrete engineering decisions.
- Scale the stack to third-party MoE models such as DeepSeek v4 and Qwen 3 to push generation speed on the models that matter in production today.
- Contribute to building AI agents that will perform GPU Engineering research and kernel optimization autonomously, calibrated to hardware target and workload, starting from the inference foundations we are building now.
- Set technical direction for a small team, raise the bar through code and reviews, and connect ambitious performance targets to work that can be shipped, measured, and iterated on quickly.
WHAT WE LOOK FOR
You have written GPU kernels for production workloads where performance was the central constraint. Showing the code is a requirement to move forward in the process.
You have operated with real ownership over difficult technical work and raised the standard of the people around you through code, reviews, and decision-making. You are comfortable carrying both individual technical depth and team-level responsibility in the same role.
Stronger signals include inline PTX or CDNA ISA in public repositories, experience with latency-sensitive execution paths, understanding of why MBU matters more than MFU at batch size 1, and a background in inference engine components. A top engineering school or a PhD with concrete GPU work counts, even without extensive industry experience.
PyTorch custom ops are an acceptable starting point if the kernels show a genuine understanding of the hardware below the framework level.
TOP 0.1% FOR THIS ROLE
The strongest candidates have already developed original judgment at the hardware boundary. They find performance wins that require going beyond what documentation exposes. They can explain why those wins worked, what tradeoffs they introduced, and how those decisions improved real token-by-token generation speed.
They shorten the loop between observation, hypothesis, implementation, and measured result. They know when to push deeper into the machine, when to change the execution plan, and when to influence model structure so the whole system moves faster. And they make the engineers around them better.
What we offer
- Direct access to AMD and NVIDIA datacenter GPUs from day one
- A team where creativity and technical judgment carry weight and where the people closest to the problem shape the key decisions
- Problems that sit on the critical path of model execution speed and that directly influence what the system can become
- Compensation aligned with top technical profiles in the Paris AI market, including equity
Our Kog Inference Engine generates 3,000 output tokens per second per request on a single 8× AMD MI300X node and 2,100 on an 8× NVIDIA H200 node (FP16, batch size 1, no speculative decoding).
We are a team of 11 people, including 10 engineers and 4 PhDs.
Test it at playground.kog.ai http://playground.kog.ai. Read the technical details on the Kog Labs blog.
The hot path is a monokernel implemented with handwritten CUDA (with PTX inline assembly) on NVIDIA, and HIP (with CDNA ISA inline assembly) on AMD.
We optimize at the low level with engine/kernel/model co-design, using reverse engineering to understand and exploit the details of how the GPU hardware works at the micro level.
WHAT YOU WILL WORK ON
You will own the technical execution of the Kog inference engine at the hardware boundary. You write code, review kernels, define performance priorities, make architecture calls, and drive a small team toward improvements that matter in production.
You move between microscopic detail and system-level judgment with the same rigor.
- Own the monokernel pipeline, the single persistent GPU program that covers the full decode pass from QKV projection to LM head sampling, across AMD and NVIDIA architectures.
- Drive low-level GPU optimization, including impossibly-fast grid synchronizations and inter-GPU collectives, and optimized GEMM and attention kernels for specific batch sizes and context lengths.
- Build and maintain profiling infrastructure inside a monokernel, including custom instrumentation, device-timestamp frameworks, and per-stage analysis to translate machine behavior into concrete engineering decisions.
- Scale the stack to third-party MoE models such as DeepSeek v4 and Qwen 3 to push generation speed on the models that matter in production today.
- Contribute to building AI agents that will perform GPU Engineering research and kernel optimization autonomously, calibrated to hardware target and workload, starting from the inference foundations we are building now.
- Set technical direction for a small team, raise the bar through code and reviews, and connect ambitious performance targets to work that can be shipped, measured, and iterated on quickly.
WHAT WE LOOK FOR
You have written GPU kernels for production workloads where performance was the central constraint. Showing the code is a requirement to move forward in the process.
You have operated with real ownership over difficult technical work and raised the standard of the people around you through code, reviews, and decision-making. You are comfortable carrying both individual technical depth and team-level responsibility in the same role.
Stronger signals include inline PTX or CDNA ISA in public repositories, experience with latency-sensitive execution paths, understanding of why MBU matters more than MFU at batch size 1, and a background in inference engine components. A top engineering school or a PhD with concrete GPU work counts, even without extensive industry experience.
PyTorch custom ops are an acceptable starting point if the kernels show a genuine understanding of the hardware below the framework level.
TOP 0.1% FOR THIS ROLE
The strongest candidates have already developed original judgment at the hardware boundary. They find performance wins that require going beyond what documentation exposes. They can explain why those wins worked, what tradeoffs they introduced, and how those decisions improved real token-by-token generation speed.
They shorten the loop between observation, hypothesis, implementation, and measured result. They know when to push deeper into the machine, when to change the execution plan, and when to influence model structure so the whole system moves faster. And they make the engineers around them better.
What we offer
- Direct access to AMD and NVIDIA datacenter GPUs from day one
- A team where creativity and technical judgment carry weight and where the people closest to the problem shape the key decisions
- Problems that sit on the critical path of model execution speed and that directly influence what the system can become
- Compensation aligned with top technical profiles in the Paris AI market, including equity
Tech stack
LLMPyTorch
About Kog SAS
Kog SAS is hiring for the lead gpu engineer role. NewJob aggregates active openings directly from Kog SAS's applicant tracking system, so this listing is current.
More jobs at Kog SAS →