Senior Kernel Generation Engineer

Requirements: A strong engineer at the intersection of AI and hardware who understands the inner workings of LLM inference at a mathematical and architectural level. LLM inference, attention, KV-cache, prefill/decode. Compute pipelines, memory hierarchy, and data movement. Kernel optimization: tiling, fusion, buffering, scheduling. Experience with FPGA / GPU / CUDA / Triton / TVM / MLIR / XLA and other accelerator architectures will be a big plus.

**Location:**📍Remote from anywhere in the world.

Contact for application: +CV

👉grab a special offer