Staff Hardware Systems Architect

DeepMind•Mountain View, CA

41d•$183,000 - $271,000

About The Position

At Google DeepMind, we've built a unique culture and work environment where long-term ambitious research can flourish. We are seeking a highly motivated Hardware Systems Architect to join our team and contribute to the development of groundbreaking datacenter infrastructure for machine learning acceleration. About us: Artificial Intelligence could be one of humanity's most useful inventions. At Google DeepMind, we're a team of scientists, engineers, machine learning experts and more, working together to advance the state of the art in artificial intelligence. We use our technologies for widespread public benefit and scientific discovery, and collaborate with others on critical challenges, ensuring safety and ethics are the highest priority. About you: We seek out individuals who thrive in ambiguity and who are willing to help out with whatever moves datacenter infrastructure innovation forward. We regularly need to invent novel solutions to problems, and often change course if our ideas don't work out, so flexibility and adaptability to work on any project is a must. The Role: In this role, you are at the forefront of designing and building the next generation of datacenter infrastructure. We are seeking a highly experienced and visionary Systems Architect to join our dynamic team. You will play a pivotal role in shaping the future of our datacenter and server architectures, from the system level down to the component selection. The ideal candidate will have a deep and broad understanding of datacenter technologies, with a proven track record of innovative design and successful implementation of large-scale, high-performance computing systems.

Requirements

10+ years of experience in systems architecture, with a primary focus on datacenter and server hardware design.
Proven track record of architecting and delivering complex, high-performance computing systems at scale.
Deep expertise in server and host architecture, including motherboard design, power delivery, and thermal management for high-power components.
In-depth understanding of datacenter power and cooling infrastructure, including both air and liquid cooling solutions at the rack and facility level.
Extensive experience with high-speed system-level interfaces (e.g.,ICI, PCIe Gen5/6, CXL, high-speed Ethernet).
Experience with system-level performance modeling and analysis.
Master's or Ph.D. in Electrical Engineering, Computer Engineering, or a related field.

Nice To Haves

Experience influencing the selection and design of SoC interfaces, with a focus on high-speed serial interconnects.
Knowledge of chiplet-based design methodologies and advanced semiconductor packaging technologies (e.g., 2.5D/3D integration).
Expertise in datacenter networking, including leaf-spine topologies and RDMA.
Working knowledge of transformer-based large language models is a plus.
Knowledge of high-performance and low-power architectures for ML acceleration.
Exceptional problem-solving and analytical skills.
Excellent written and verbal communication skills, with the ability to present complex technical concepts to a variety of audiences.
Strong leadership and collaboration skills, with the ability to influence and guide cross-functional teams.

Responsibilities

Lead the architectural design of large-scale, high-density server platforms, considering system topology, power distribution, advanced cooling methodologies, and mechanical constraints.
Architect the physical, electrical, and thermal design of server racks, hosts, trays, and other datacenter hardware from concept to deployment.
Drive system-level decisions for host and server architecture, including motherboard design, power delivery, memory subsystems, and high-speed interconnects
Oversee and steer the design and development of complex printed circuit boards, ensuring signal and power integrity for cutting-edge interconnects and components.
Define and analyze system requirements for reliability, availability, and serviceability (RAS) at the server and rack level.
Develop and analyze system-level performance models to guide architectural trade-offs between performance, power, and cost.
Collaborate with software and firmware teams to ensure seamless integration and co-optimization across the entire system stack.
Lead cross-functional teams to drive technical alignment and decision-making from concept to high-volume deployment.