Sandisk

Senior Principal AI System Architect

Milpitas, California, United StatesFull timeStaffPosted about 2 months ago
Apply on Sandisk →Sign in to save this role

Sign in to see who you know at Sandisk.

Sandisk understands how people and businesses consume data and we relentlessly innovate to deliver solutions that enable today’s needs and tomorrow’s next big ideas. With a rich history of groundbreaking innovations in Flash and advanced memory technologies, our solutions have become the beating heart of the digital world we’re living in and that we have the power to shape.Sandisk meets people and businesses at the intersection of their aspirations and the moment, enabling them to keep moving and pushing possibility forward. We do this through the balance of our powerhouse manufacturing capabilities and our industry-leading portfolio of products that are recognized globally for innovation, performance and quality.Sandisk has two facilities recognized by the World Economic Forum as part of the Global Lighthouse Network for advanced 4IR innovations. These facilities were also recognized as Sustainability Lighthouses for breakthroughs in efficient operations. With our global reach, we ensure the global supply chain has access to the Flash memory it needs to keep our world moving forward. A System Architect focusing on advanced memory technology and AI Inference solution infrastructure will lead the definition of system level solutions with emphasis on compute memory bottlenecks, bandwidth and latency management. The job also requires analyzing workload requirements and mapping them to hardware technologies and architecture while optimizing performance, power efficiency, and scalability. Such an architect works at the intersection of chiplet design, SoC, and software co-design. Essential Duties and Responsibilities:Architecture Design and Specifications: focus on system level architecture that is co-optimized with SoftwarePerformance and Power Optimization: Developing system level performance and power models with the ability to assist in making customer specific trade-offsWorkload Analysis: Mapping AI/ML models to hardware requirementsHardware/Software Co-design: Collaborate with software and hardware teams to ensure seamless integration of memory subsystems, cache hierarchies, and system interconnectsAdvanced Memory solutions: Explore novel technologies and architectures such as in-memory and near-memory computing, and innovative packaging solutions.Technical leadership: Able to guide design teams, produce technical documentation, IP designs, and clearly articulate and drive key concepts to a broad technical audience. Required: Master's or Ph.D. in Electrical Engineering, Computer Engineering, or Computer Science10+ years in System Architecture, SoC Design, and memory system development.Deep knowledge of various memory technologies including DRAM, DDR, LPDDR, GDDR, NANDAn good understanding of AI accelerators, GPU, and Neural Processing EnginesProficiency in C/C++, Python, RTL design, and system-level modelingStrong working knowledge of various interconnect technologies including PCIe, CXL, NoCs, ethernet, RDMAExce...

Read the full posting on Sandisk →