This PhD position at ETH Zürich focuses on developing energy-efficient machine learning methods for wearable and augmented reality (AR) systems. The research is situated at the intersection of machine learning, embedded intelligence, and human–computer interaction, aiming to create adaptive, efficient, and context-aware learning systems for next-generation wearable and AR platforms. The project emphasizes the development of novel machine learning models that can learn from limited resources, adapt locally to users and environments, and maintain computational efficiency. These models will be benchmarked in software, with selected approaches implemented as embedded prototypes to demonstrate real-world feasibility.

The overarching goal is to bridge high-level algorithmic innovation with energy-aware hardware deployment, enabling intelligent sensor systems that function as autonomous micro-agents for perception and communication. The position is part of the SNSF Ambizione project MiNI – Multimodal Neuromuscular Interface, in collaboration with Scuola Superiore Sant'Anna in Pisa and Imperial College London. MiNI aims to develop a platform for real-time neuromuscular signal interpretation by integrating electrical (sEMG), mechanical (ultrasound), and complementary sensor data for high-fidelity movement estimation, thus enabling natural and efficient human–machine interaction. The PhD research will focus on several core directions: pretraining strategies and domain adaptation for ultrasound and other modalities; multimodal sensor fusion frameworks; lightweight, real-time models using quantization and compression; hardware–algorithm co-design for embedded deployment; and distributed embedded AI with networks of autonomous micro-agents.

The successful candidate will conduct both experimental and theoretical research, implement and validate methods on embedded platforms, collaborate with experts in embedded systems and digital IC design, and contribute to end-to-end human–computer interaction demonstrators. The position also involves publishing in leading journals and conferences and supervising Bachelor’s and Master’s students. Applicants should have a Master’s degree in computer science, electrical engineering, or a related field, with a strong background in machine learning, deep learning, and optimization.

Experience with embedded platforms, signal processing, or model compression is a plus. Strong programming skills in Python and C/C++ are required, and familiarity with ML deployment frameworks is advantageous. The Digital Circuits and Systems Group at ETH Zurich offers a dynamic research environment focused on energy-efficient computing, from ultra-low-power IoT nodes to high-performance systems. ETH Zurich is committed to diversity, sustainability, and providing an inclusive environment for all staff and students.

Applications must be submitted online with the required documents as separate PDFs, following strict naming conventions. Further information about the Integrated Systems Laboratory is available on the ETH Zurich website.