NPU Architect

About the Role

In this role you'll be responsible to design the next iteration of SEMRON's 3D in-memory compute chip. You will collaborate with a team of hardware, compiler and ML engineers to optimise all aspects of executing ML workloads based on our capacitive analog in-memory matrix-vector multiplication units.

What you will do:

• Design and specify the structure and internal organisation of core architecture modules, aligned with workload requirements and software deployment processes.
• Partner with the software team to evaluate module performance and efficiency for key workloads, uncover performance constraints, and inform architectural choices.
• Monitor emerging trends and research in AI workloads, hardware architectures, and applications to guide the evolution of next-generation architectures.

What you should bring in:

• BS/MS/PhD in EE, CS, or a related field
• Understanding in computer architecture, digital design, and micro-architecture concepts
• Familiarity with AI/ML algorithms, frameworks, and workloads
• Programming experience in C/C++ and Python

Helpful but not required:

• Hands-On Experience with ML Hardware Exploration Frameworks like Timeloop, ZigZag, etc.
• Hands-On Experience with HDLs such as Verilog or System Verilog

About us

At SEMRON, we’re redefining what’s possible in AI hardware. Our core innovation lies in analog in-memory computing for deep neural network acceleration, enabling us to build compute architectures that scale vertically into the third dimension, much like NAND flash revolutionized memory. This leap in physical density allows us to deploy models with billions of parameters on chip areas as small as a few square millimeters.