Master's Thesis: Advanced AI Accelerators

Location: Kista, Sweden; project location: Stockholm, Sweden

Company

hirify.global Sweden R&D develops telecommunications, network solutions, and 6G wireless systems through R&D centers in Sweden.

What you will do

• Develop a simulation framework for power and thermal analysis of 3D-integrated computing systems used in AI accelerators.
• Integrate architectural simulators such as gem5 with power estimation models and thermal simulation tools such as HotSpot.
• Evaluate conventional and emerging memory technologies, including advanced SRAM and MRAM.
• Investigate how memory technologies, reinforcement-based task scheduling, and workload characteristics affect power consumption, performance, and temperature distribution in AI SoCs.

Requirements

• Master's student available to start in spring 2027.
• Background in Computer Engineering or Electrical Engineering.
• Basic knowledge of computer architecture and programming in Python and C++.
• Strong spoken and written English is required.
• Ability to work effectively both independently and in a team.
• High attention to detail and commitment to producing high-quality work.

Nice to have

• Familiarity with gem5, HotSpot, or McPAT.
• Knowledge of memory technologies and 3D integration.

Culture & Benefits

• Work with R&D engineers on advanced 6G and AI accelerator technologies.
• Collaborate with engineers worldwide while contributing independently to a research project.
• Contribute to real-world technology development focused on power, performance, and thermal challenges.