Agentic Compiler Engineer

Company hidden

Paris, France Remote Full-time Posted 2w ago

We developed Laneformer 2B and Delayed Tensor Parallelism (DTP), a Transformer architecture designed to overlap communication with computation. Our inference stack 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 at batch size 1, without quantization or speculative decoding. Our next challenge is making model optimization faster and more scalable. New models are released constantly, and spending months adapting each one to a specific GPU setup is not sustainable. This is why we're developing AGCO, our agentic compiler…

See the company and apply

Unlock to see who’s hiring, read the full description and apply on the company site.

Checking access…

See how well you match this job

Upload your resume and we’ll score your fit for this role and 6 similar roles — then tailor your CV to it with AI. Free, no credit card.

Check your match

Similar jobs

Explore related jobs

Want more roles like this? Browse fresh jobs or tailor your resume with AI.