Lead SoC Architect

Speedata.io · israel

Speedata is modernizing analytics infrastructure with the first purpose-built ASIC processor, the Analytics Processing Unit (APU), for analytics and AI data workloads. Delivering up to 100x faster Apache Spark performance while cutting infrastructure TCO by 90%, the APU executes analytics operations directly in silicon with seamless integration and no code changes. Requirements BSc or higher degree in Electrical Engineering, Computer Science or Computer Engineering. Graduated with honors. 6+ years of experience as a system architect for large, high-end ASIC SoCs. Experience with multidisciplinary HW/SW systems. Team player with great communication skills. Advantages Deep understanding of datacenter systems Experience with architecture of processors, accelerators, high speed PCIe Responsibilities Definition and detailed hardware specifications of subsystems in the SoC Breaking down the sub-system architecture into microarchitectural blocks with the related firmware, and SW components. Understanding the system in which the SoC is integrated to and designing the SoC to perfectly fit into the datacenter system. Speedata is the creator of the Analytics Processing Unit (APU), the first processor purpose-built for Apache Spark SQL, batch ETL, and AI data preparation workloads. By executing Spark operations natively in silicon rather than memory, the APU delivers up to 100x faster performance and 90% lower total cost of ownership compared to general-purpose compute, with zero code changes required. In one enterprise AI data preprocessing deployment, customers replaced 37 servers with just 3. Speedata integrates directly into existing data pipelines, accelerating the most demanding analytics and AI data layer workloads at scale. Our hardware, the C200 APU card with the Callisto ASIC on PCIe Gen 5, delivers transparent acceleration for Spark SQL, DataFrame, and batch ETL workloads.

Apply »