PhD in Computer Architecture for Real-Time AI at the Edge

# PhD Position: Computer Architectures for AI on Embedded and Edge Systems

Join the NWO Perspectief FIND program and help design next-generation computer architectures for running large AI models on embedded and edge systems under strict timing, energy, and memory constraints.

## Overview
This PhD position focuses on the design of novel computer architectures to enable foundation models (large AI models) to run on embedded and edge systems with guaranteed real-time performance, energy efficiency, and minimal memory footprint. Industrial edge deployments—in semiconductor manufacturing, printing systems, automotive radar, smart mobility cameras, and HealthTech—require on-device AI to ensure low latency, privacy, and resilience.

## Research Focus

• Design of novel computer architectures for embedded and edge deployment of AI models
• Hardware-aware optimization and co-design with accelerators (FPGAs, GPUs, near-memory systems)
• Model compression techniques (pruning, quantization, token merging, sparsity exploitation)
• Joint optimization of algorithms and hardware for predictable real-time performance
• Prototyping and validation in collaboration with leading semiconductor manufacturing companies
• Shift from "best-effort" execution to deterministic, deadline-compliant AI inference

## Work Environment
Embedded in the Electronic Systems (ES) group within the Electrical Engineering department at Eindhoven University of Technology (TU/e). Close collaboration with ASMPT and other leading high-tech industry partners including ASML, NXP, Canon, Technolution, Signify, Shell, Stryker, TNO, and others.

## Key Responsibilities

• Conduct research on computer architecture design for edge AI deployment
• Explore hardware-software co-optimization
• Prototype and validate architectures with industry partners
• Contribute to teaching tasks (minimum 10%, maximum 15% per year)
• Develop into an autonomous scientific researcher