d-MATRiX

d-MATRiX is developing a novel hardware system and a full-stack software solution to accelerate large-scale modern deep neural network compute workloads for the cloud. Leveraging a unique combination of in-memory computing and digital signal processing system design, in-memory compute array design, and on-chip and chip to chip interconnect fabric, d-MATRiX's AI compute engine holds the promise of drastically improving power-efficiency and compute latency of cloud inference workloads, by orders of magnitude compared to competition. The Machine Learning Team is responsible for the R&D of core algorithm-hardware co-design capabilities in d-MATRiX's end-to-end solution. You will be joining a team of exceptional people enthusiastic about researching and developing state-of-the-art efficient deep learning techniques tailored for d-MATRiX's AI compute engine. You will also have the opportunity of collaboration with top academic labs, and help customers to optimize and deploy workloads for real-world applications on our systems. For questions, please reach out at twebb@d-matrix.ai