PhD Position (f/m/d) - Memory-Centric NPU Architectures and Emerging Memory Technologies for Edge AI
Core
Researching memory-centric NPU architectures and emerging memory technologies to improve performance, power efficiency, and scalability for edge AI and embedded Generative AI systems.
Role type
PhD researcher (hardware/software co-design)
Builds
Next-generation NPU subsystem architectures and evaluation frameworks
Domain
Computer architecture, semiconductor memory systems, AI accelerators, embedded systems
Deliverable
research
Required skills
computer architecture, digital design, embedded systems, semiconductor memory systems, AI accelerators and NPUs, hardware/software co-design, digital hardware design
Preferred skills
RTL development (Verilog/SystemVerilog/VHDL), FPGA prototyping, computer architecture simulators, memory hierarchy optimization, eDRAM/GCRAM/MRAM/ReRAM/CXL knowledge
Technologies
Python, C/C++, eDRAM, GCRAM, MRAM, ReRAM, CXL
Responsibilities
Conduct research on next-generation NPU subsystem architectures, develop architectural modeling and simulation frameworks, investigate integration of emerging memory technologies, build PPA evaluation methodologies, evaluate real-world AI workloads (CNNs, Transformers, LLMs, VLMs), analyze trade-offs across performance/power/area/scalability, publish results in leading conferences and journals, collaborate with experts in semiconductor design and AI acceleration
Seniority
PhD candidate, research-focused