Staff SoC Architect, AI Data Center

Qualcomm•San Diego, CA

1d•$155,400 - $233,200

About The Position

Qualcomm’s Data Center AI Architecture team defines next-generation cloud AI system-on-chip (SoC) and systems for generative AI inference workloads that demand exceptional compute, memory bandwidth, capacity, and system scalability. We are seeking exceptional architects to help shape multiple generations of AI accelerators and complete data center systems, with a strong focus on SoC, memory, and system architecture and technologies. If you are passionate about solving complex architecture challenges in a collaborative, multidisciplinary environment while contributing to building a substantial new business for one of the leading system-on-chip and computer architecture companies in the industry, we want to hear from you.

Requirements

Bachelor's degree in Electrical Engineering, Computer Science, or related field and 4+ years of Systems Engineering or related work experience.
OR Master's degree in Electrical Engineering, Computer Science, or related field and 3+ years of Systems Engineering or related work experience.
OR PhD in Electrical Engineering, Computer Science, or related field and 2+ years of Systems Engineering or related work experience.
2+ years of experience in one or more system architecture technology areas and products (e.g., Power System, Shared Resource Management, Limits/Thermal Management, Hardware Islands).

Nice To Haves

MS or PhD in EE, ECE, CE, CS, or a related field
7+ years of relevant experience in SoC, platform, or system architecture; AI accelerators; memory architecture; or memory technologies
Ability to collaborate across teams, build alignment, and contribute to technical direction
Computer and system architecture expertise spanning one or more of processors, accelerators, memory systems, data center network fabrics, interconnects, hardware/software interfaces, platform topology, and SoC and system implementation tradeoffs
Ability to execute quantitative SoC, system, and competitive studies using high-level calculators, spreadsheets, analytical models, profilers, and functional or performance simulators
Experience developing architecture methodologies, tools, and analysis frameworks and translating findings into actionable recommendations
Experience correlating modeled and measured system performance, isolating hardware and software bottlenecks, and driving cross-functional performance closure through production
Excellent technical communication, documentation, and interpersonal skills, including presenting to technical and business stakeholders
Self-directed execution, mentorship of others, and rigorous attention to accuracy
Understanding of generative AI and machine-learning workloads, especially Large Language Model inference and accelerator bottlenecks
Experience in processor, accelerator, or system architecture, including ISA design, microarchitecture, performance modeling, system topology, scale-up or scale-out networks, or hardware/software co-design
Knowledge of DRAM and memory-controller architecture, bandwidth, latency, and power tradeoffs, protocols such as LPDDR, HBM, DDR, or GDDR, and emerging technologies such as processing-in-memory, processing-near-memory, or 3D integration
Expertise in one or more data center SoC or system technologies such as RAS, ECC, security, encryption, Ethernet or InfiniBand networking, RDMA, network interface controllers, switches, congestion control, chip-to-chip or die-to-die protocols, chiplets, PHYs, power and thermals, advanced packaging, platform management, or system scalability
Programming ability for architecture modeling and automation; object-oriented C++ and Python preferred
Fluent with using AI to accelerate workflows

Responsibilities

Partner across architecture, design, systems, product, software, platform, and customer teams to deliver market-leading data center systems
Translate product and workload requirements into SoC and system specifications, and drive feature-set requirements into technology, IP, platform, and software teams
Execute SoC and system architecture studies, product definition, and implementation guidance, quantifying performance, power, area, cost, capacity, memory bandwidth, network topology/bandwidth/latency, and scalability tradeoffs while driving analysis methods and tools
Follow designs through implementation and production, correlate observed system performance with models and targets, identify root causes of gaps, and drive performance to closure
Execute competitive analysis across SoC, platform, system, compute, memory, data center networking, software, and deployment considerations
Support and mentor technical contributors and generate innovations and patents