AI System Architect (NPU / GPU / Interconnect)
Qualcomm · Shanghai, China ·
- Work mode
- Onsite
- Category
- Architecture
- Experience
- 6+ years
Company:
Qualcomm China
Job Area:
Engineering Group, Engineering Group > ASICS EngineeringGeneral Summary:
We are seeking experienced architects with deep expertise in AI accelerators (NPU), GPUs, and/or high-performance system interconnects to define next-generation AI and data center compute platforms.
Successful candidates will possess strong architectural knowledge in one or more of the following areas:
- AI accelerator and NPU architecture
- GPU architecture, graphics, and compute systems
- High-performance system interconnects and data center fabrics
Key Responsibilities
Customer & Platform Architecture
- Engage with customers, partners, and internal stakeholders to understand AI workload requirements, deployment scenarios, performance targets, and system constraints.
- Translate customer and market requirements into scalable system architecture, technology roadmaps, and platform features.
- Drive architecture tradeoff analysis across performance, power, cost, scalability, and deployment requirements to influence product direction.
One or More of the Following Domains:
AI / NPU Architecture
- Analyze and optimize AI workloads including LLMs, Transformers, computer vision, multimodal AI, and recommendation systems.
- Drive HW/SW co-design across architecture, compiler, runtime, driver, and framework layers.
- Lead performance analysis and optimization across compute, memory, and communication subsystems.
GPU & Graphics Architecture
- Analyze graphics, rendering, compute, and AI workloads to optimize performance, efficiency, and scalability.
- Drive architecture of GPU compute pipelines, graphics pipelines, memory systems, scheduling, and data movement.
- Collaborate with graphics software, driver, runtime, and application teams to optimize workload execution and user experience.
System Interconnect & Data Center Architecture
- Architect high-performance data movement across compute, memory, storage, and networking subsystems.
- Define scale-up and scale-out architectures using PCIe, CXL, Ethernet, UALink, or similar communication fabrics.
- Drive architecture of cache-coherent fabrics, memory hierarchies, chiplet communication, and distributed AI systems.
- Lead system-level architecture decisions for scalability, performance-per-watt, latency, and overall system efficiency.
Required Qualifications
- BS/MS in Electrical Engineering, Computer Engineering, Computer Science, or related field.
- 10+ years of experience in AI accelerator, GPU, high-performance compute, system architecture, or related disciplines.
- Deep expertise in one or more of the following areas:
- AI accelerator / NPU architecture
- GPU architecture, graphics pipeline, and compute architecture
- High-performance interconnects and communication fabrics
- Data center system architecture
- Memory hierarchy and bandwidth optimization
- AI workload performance analysis and modeling
- Strong HW/SW co-design background with a solid understanding of how AI software stacks, compilers, runtimes, and drivers utilize underlying hardware resources.
- Demonstrated ability to drive architecture decisions across hardware, software, memory, and communication subsystems.
Language Requirements
- Fluent in both Mandarin Chinese and English.
- Able to lead technical discussions and collaborate effectively across global engineering teams.
Minimum Qualifications:
• Bachelor's degree in Science, Engineering, or related field and 8+ years of ASIC design, verification, validation, integration, or related work experience.OR
Master's degree in Science, Engineering, or related field and 7+ years of ASIC design, verification, validation, integration, or related work experience.
OR
PhD in Science, Engineering, or related field and 6+ years of ASIC design, verification, validation, integration, or related work experience.
Qualcomm is an equal opportunity employer. If you are an individual with a disability and need an accommodation during the application/hiring process, rest assured that Qualcomm is committed to providing an accessible process. You may e-mail [email protected] or call Qualcomm's toll-free number found here. Upon request, Qualcomm will provide reasonable accommodations to support individuals with disabilities to be able participate in the hiring process. Qualcomm is also committed to making our workplace accessible for individuals with disabilities. (Keep in mind that this email address is used to provide reasonable accommodations for individuals with disabilities. We will not respond here to requests for updates on applications or resume inquiries).
Qualcomm expects its employees to abide by all applicable policies and procedures, including but not limited to security and other requirements regarding protection of Company confidential information and other confidential and/or proprietary information, to the extent those requirements are permissible under applicable law.
To all Staffing and Recruiting Agencies: Our Careers Site is only for individuals seeking a job at Qualcomm. Staffing and recruiting agencies and individuals being represented by an agency are not authorized to use this site or to submit profiles, applications or resumes, and any such submissions will be considered unsolicited. Qualcomm does not accept unsolicited resumes or applications from agencies. Please do not forward resumes to our jobs alias, Qualcomm employees or any other company location. Qualcomm is not responsible for any fees related to unsolicited resumes/applications.
If you would like more information about this role, please contact Qualcomm Careers.