Senior Staff LLM Inference Engineer

About d-Matrix

d-matrix.ai

d-Matrix is building ultra-low latency, batched inference for Generative AI through an efficient memory–compute integration—the world’s first of its kind. By unifying memory and compute, their solution accelerates large language models and other generative workloads with high throughput and lower power consumption. The platform aims to make Generative AI inference blazing fast, sustainable, and commercially viable at scale for enterprises. Positioned as a memory-centric AI acceleration pioneer, d-Matrix enables faster, more cost-effective AI service deployments.