PROTON Lab at School of Electrical, Computer and Energy Engineering — ASU ECEE is seeking a highly motivated PhD student to pursue research in the area of machine learning for fault-tolerant computing systems. The position offers the opportunity to work on cutting-edge challenges at the intersection of hardware-software co-design, anomaly detection, and system resilience.
The successful candidate will focus on designing and implementing advanced machine learning methods for analyzing hardware and software telemetry under fault conditions.
Research directions include:
- Developing unsupervised and deep learning models to detect anomalous system behaviors.
- Investigating dual-model anomaly detection strategies tailored to different classes of computing architectures (ASICs vs. microprocessors).
- Leveraging telemetry such as privilege transitions, performance counters, and execution traces to quantify robustness of microarchitectures.
- Fusing multi-abstraction data (gate-level, architectural, and software execution traces) using ML-based approaches for improved anomaly detection.
- Designing predictive algorithms that highlight emergent fault propagation patterns not easily captured by deterministic analysis.
Candidate Profile
- Strong background in Electrical/Computer Engineering, Computer Science, or a related discipline.
- Solid understanding of machine learning and anomaly detection, with experience in deep learning frameworks (e.g., PyTorch, TensorFlow).
- Familiarity with hardware architectures, FPGA-based platforms, or hardware-software co-design is desirable.
- Strong programming and data analysis skills.
- Excellent communication skills and motivation for interdisciplinary research.
- Candidates must be based in the United States, with preference for U.S. citizens due to project constraints.
Opportunities
- Join an internationally recognized research program in machine learning for resilient and secure computing systems.
- Access to advanced hardware-software platforms and experimental infrastructures.
- Publish in top conferences and journals in machine learning, computer engineering, and system reliability.
- Benefit from ASU’s strong collaborative research environment and mentoring.
Interested applicants should send a CV, a brief research statement, and the contact information of references at eirini@asu.edu
Strict start date: Spring 2026
