Agentic Compiler Engineer
- Type
- Job
- Organization
- Kog
- Location
- Paris, France
- Deadline
- Rolling or not stated
- Who can apply
- On-site in Paris, France
- Posted
- 29 September 2026
About this Opportunity
ABOUT KOGKog builds a co-designed inference stack for real-time AI agents on standard datacenter GPUs, spanning model architecture, inference engine, compilers, and low-level GPU kernels.On the model side, we developed Laneformer 2B and Delayed Tensor Parallelism (DTP), a Transformer architecture that overlaps communication with useful computation and weight streaming.On the systems side, the Kog Inference Engine runs this stack on standard AMD and NVIDIA datacenter GPUs.Kog generates 3,500 tokens/s per request on 8 AMD MI300X GPUs and 2,100 tokens/s per request on 8 NVIDIA H200 GPUs, in FP16
Documents you may need
- Updated CV / Resume
- Cover Letter (tailored to this role)
How to apply
- Click the "Apply — via Arbeitnow" button to go to the source page.
- Read the full description and confirm you meet the requirements.
- Prepare your CV and cover letter tailored to this role.
- Submit your application through the official portal.
- Follow up within 1–2 weeks if you do not hear back.