GPU Engineer
Kog Is this your company? Claim it · Paris, France · Full-time
Description
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 imple…
View full original posting → Source: Arbeitnow
How to apply
- Read the description and requirements and check the location and pay.
- Click “Apply now” on this page. If you do not have a free account yet, create one — it takes about a minute.
- Keep your phone on and your CV or details ready, so the employer can reach you.
- You can also open the original posting (link above) to see how the employer prefers applications.
- Never pay money to get a job. Report any listing that asks you to.
Questions about this job
Where is this GPU Engineer job located?
The listing places this job in Paris, France.
Who is hiring?
The employer shown on the listing is Kog.
What is the salary?
The listing does not state a salary. Ask the employer about pay, overtime and payment dates before accepting.
Is it full-time or part-time?
The listing type is Full-time.
When was this job posted?
It was posted on 10 November 2026. Jobs that stay open too long are closed automatically, so apply soon if you are interested.
How do I apply?
Read the description and requirements, then click Apply now on this page (a free account is needed). You can also open the original posting to see how the employer takes applications.
Do I have to pay to apply?
No. Applying on Get Mazdoor is free, and a genuine employer does not ask for money to apply or for a "registration" or visa fee before an offer. If anyone asks you to pay, do not.
More jobs in Paris
Similar Engineer jobs
Browse more: Jobs in Paris · Engineer jobs · All jobs in Pakistan
