NoC Power Modeling Intern | AI/ML for PPA

QUALCOMM, Inc.; Guyancourt; On-site; EUR 12,000 - 17,000; Full time

Benefits offered by this job

Paid internship

Job summary

Qualcomm France S.A.R.L. in Guyancourt is offering a 6-month paid internship in the Interns Group. You will research the impact of power management on NoC architectures and develop an AI/ML-based power modeling framework to estimate power during early design stages.

The project covers the design of control-plane NoC with power-management IPs, data-driven power characterization, and training ML models (ANN/MLP, RF, GNN) to enable fast, power-aware exploration.

Qualifications

• Final-year master's degree in Microelectronics, Computer Engineering or related field.
• Strong scripting in Python and bash; familiarity with Verilog/VHDL, UVM, and ML frameworks is a plus.
• Proficient in English; able to communicate in a technical environment.

Responsibilities

• Design & scenario setup for power-management NoC with IPs and traffic scenarios.
• Perform power characterization using synthesis and timing simulations.
• Construct a labeled dataset mapping traffic, activity, frequency and architecture to power.
• Train and compare ML models (ANN/MLP, RF, GNN) for power modeling.
• Support design-space exploration using trained models to guide architecture decisions.

Skills

Python

Bash

Verilog/VHDL

UVM

ML frameworks

English proficiency

Education

Final-year master’s degree in Microelectronics or Computer Engineering

Tools

NoC/IPS design

EDA flows

Power estimation tools

Job description

Qualcomm France S.A.R.L. in Guyancourt is offering a 6-month paid internship in the Interns Group. You will research the impact of power management on NoC architectures and develop an AI/ML-based power modeling framework to estimate power during early design stages.

The project covers the design of control-plane NoC with power-management IPs, data-driven power characterization, and training ML models (ANN/MLP, RF, GNN) to enable fast, power-aware exploration.