Silicon AI/ML Architect, TPU, Google Cloud

Google is seeking a Silicon AI/ML Architect to join their Technical Infrastructure team, focusing on TPU (Tensor Processing Unit) development for Google Cloud. This role combines hardware architecture expertise with machine learning specialization, working on custom silicon solutions that power Google's future products. The position requires deep understanding of SoC architecture, AI/ML systems, and hardware-software integration.

As a Silicon AI/ML Architect, you'll be at the forefront of developing cutting-edge AI accelerator architectures, working with multi-chiplet SoC designs, and optimizing performance for next-generation AI applications. You'll collaborate with diverse teams across systems, software, verification, and silicon validation to ensure optimal design implementation.

The role offers the opportunity to impact millions of users worldwide through Google's direct-to-consumer products and cloud services. You'll be working with state-of-the-art technology in AI acceleration, contributing to Google's data center infrastructure, and helping shape the future of machine learning hardware.

This position is ideal for experienced architects who are passionate about pushing the boundaries of AI hardware design, have a strong background in SoC architecture, and enjoy working at the intersection of hardware and machine learning. You'll be part of Google's prestigious Technical Infrastructure team, known for innovation and engineering excellence in maintaining and advancing Google's vast technical infrastructure.

The role combines technical leadership with hands-on architecture work, requiring both deep technical expertise and strong collaborative skills. You'll be instrumental in making strategic decisions that balance performance, power, and cost considerations while driving Google's AI hardware roadmap forward.