Lead GPU Engineer for Fast Inference

Kog is hiring for a hands-on leadership role focused on optimizing its inference engine at the hardware boundary. This position requires expertise in GPU kernel development, understanding of memory hierarchy, and the ability to influence architectural decisions. You will work closely with a small team on critical aspects that determine token generation speed, guaranteeing measurable performance improvements. The company offers remote-first working conditions with regular time overlap for collaboration and competitive compensation aligned with the top Paris AI market standards.

#J-18808-Ljbffr