FY27 Intern - AI-Driven Power Modeling for NoC IP Power Evaluation (6 months)
QualcommJob Title
FY27 Intern - AI-Driven Power Modeling for NoC IP Power Evaluation (6 months)
Role Summary
Internship in Qualcomm's QITC group to develop an AI/ML-based framework that estimates power consumption of Network-on-Chip (NoC) IP architectures during early design stages. The role supports fast exploration of design choices to inform power-aware architecture decisions.
Work is hands-on: combine synthesis/simulation-based power characterization with machine learning to produce datasets, models, and a prototype exploration tool.
Experience Level
Entry-level (Internship). Targeted at final-year master's students or equivalent early-career candidates; no specific years of professional experience required.
Responsibilities
The intern will deliver an automated characterization flow, datasets, ML models, and a prototype exploration tool. Key activities include:
- Define NoC architectures, topologies and representative traffic scenarios for evaluation.
- Run synthesis and simulations to obtain activity profiles and gate-level power measurements.
- Construct and label datasets from characterization results for ML training.
- Train, compare and validate AI/ML models against gate-level references for accuracy and speed.
- Integrate models into a fast exploration prototype to evaluate design options in seconds.
- Document methodology, model accuracy, and recommended guidelines for power-aware NoC choices.
Requirements
Technical skills and tools expected for successful completion of the internship:
- Proficient scripting in Python; familiarity with shell scripting (bash).
- Familiarity with digital design concepts and EDA flows; notions of Verilog/VHDL and UVM are a plus.
- Experience with machine learning frameworks and model training workflows.
- Ability to run and analyze synthesis and simulation outputs; data preprocessing and dataset construction skills.
- Strong problem-solving, documentation skills, and proficiency in English.
- Ability to work independently under a six-month internship timeline.
Education Requirements
Final-year Master's degree in Microelectronics, Computer Engineering, or a related technical field; equivalent practical experience will be considered. (The posting specifically targets candidates completing a master's program.)
About the Company
Company: Qualcomm
Headquarters: San Diego, California, United States
Qualcomm is a global leader in semiconductor and telecommunications equipment, specializing in mobile technologies and innovations. Known for its Adreno GPUs, the company provides solutions enabling advancements in mobile gaming, AI, VR/AR, and autonomous driving. Qualcomm's cutting-edge technology and commitment to high-performance, power-efficient designs drive the evolution of mobile graphics and connectivity worldwide.
