3D Memory Chip Architect and Design, Principal Engineer

Qualcomm•San Diego, CA

3d•$192,000 - $288,000

About The Position

Qualcomm Custom Memory Team in Process & Package Solutions Group has an opening in the areas of 3D Memory Design and Architecture for memory-centric compute systems for data center, mobile, compute, and XR. The candidate will assess and optimize the 3D Memory architectures to improve system KPIs such as bandwidth, latency, power, thermal, and area efficiency. The candidate will explore the best organization of near-memory processing units along with the system and memory buses so that the extreme bandwidth of 3D Memory will be fully utilized across the compute fabric for cloud, compute, mobile and IoT as well as studying how to interconnect those memory cubes using scale-up and scale-out fabrics. The candidate will work on solutions on 3D integration of both memory and compute blocks in power, thermal, and 3D fabric restrictions. The candidate is expected to understand the concepts of memory bank organization and signaling, bus, IO, and compute fabrics as well as advanced packaging and 3D integration. This position offers the opportunity to work across multiple organizations such as process and packaging team, AI and compute architects, memory controller team, global SoC team, performance modeling teams, and emulation team. Providing timely feedback and updating architecture and design trade-offs to the team is essential.

Requirements

Bachelor's degree in Science, Engineering, or related field and 8+ years of ASIC design, verification, validation, integration, or related work experience.
Master's degree in Science, Engineering, or related field and 7+ years of ASIC design, verification, validation, integration, or related work experience.
PhD in Science, Engineering, or related field and 6+ years of ASIC design, verification, validation, integration, or related work experience.

Nice To Haves

Experience in RTL, circuit and system design to be able to model and optimize dataflow
Experience in SoC architecture and power/clock/bus design
Experience in DRAM/FLASH architecture performance assessment
Experience in memory circuit design (SRAM/DRAM/FLASH/ROM/OPT, etc)
Experience in programming language (C/C++/Phyton) or scripting language (Perl/Python)
Ability to develop Verilog/Verilog-A/Verilog-AMS models of critical dataflow is strong plus
Familiar with the DRAM/FLASH datasheets and IO interfaces
Experience in ASIC design, mixed-signal design, and performance modeling
Good knowledge of memory architecture, buses, and 2.5D/3D integration
Proficiency in use of EDA tools, Matlab, and Phyton
Master's or Ph.D. in Electrical Engineering, Computer Science, or a related field
Self-Starter with good communication skills and team-working spirit
Strong problem-solving and analytical skills
Ability to work independently and as part of a team

Responsibilities

Develop and optimize 3D DRAM/FLASH organization and near-memory computing architectures to achieve high density, high TOPS/mm2, and high TOPS/W
Develop and validate models for 3D Memory performance, power, and yield as function of bank, TSV, and power distribution choices
Develop novel fabrics for best/robust distribution of high-bandwidth data from 3D DRAM memory arrays to the near-memory computing units across various workloads for mobile, compute, and XR applications
Develop power distribution topology that enable robust memory operation in the 3D stack
Simulate and emulate system performance of 3D memory architecture choices across AI, compute, and mobile workloads
Floorplan 3D memory chips and design memory array control structures under 3D integration manufacturing constraints, testability, repairability, and high performance
Knowledge about chip connection fabrics such UCIe, UAL, LPDDR, HBM3/4 and PCIe