LLM Inference Engineer

The LLM Inference Engineer role at a US-Israeli AI startup involves owning the end-to-end LLM serving stack on custom hardware, optimizing frameworks like vLLM and SGLang for peak performance. The position requires bridging cutting-edge silicon with production-grade AI, focusing on distributed inference, multi-modal pipelines, and performance optimization. This high-impact role directly influences kernel, compiler, and hardware development by identifying and resolving bottlenecks.