Profile photo

Aaron Zhao

Computer Scientist & AI Researcher

Download CV

Timeline

2022 -- Present
Assistant Professor, Imperial College London
Department of Electrical and Electronic Engineering. Leading the DeepWok Lab — a research lab focused on efficient AI, hardware-algorithm co-design, and AI security — with 10+ PhD and 10+ Master students and collective PI/Co-I funding above £10M.
Sep 2025 -- Present
Co-founder, Sequrity AI
Building the first secure AI agentic flows.
2022 -- Present
Visiting Researcher, University of Cambridge
Maintaining close ties with the Computer Laboratory.
2017 -- 2022
PhD in Computer Science, University of Cambridge
Supervised by Prof. Robert Mullins. Thesis: Software and Hardware Co-design for Efficient Neural Networks.
2021 -- 2022
Junior Research Fellow, St John's College, Cambridge
College research fellowship in computer science.
Dec 2021 -- Jun 2022
AI/ML Scholar & Part-time Researcher, Apple
Selected as an Apple Scholar in AI/ML (2020). Worked on hardware-aware neural network optimization, efficient inference for on-device ML, and building security filters.
Jun 2019 -- Jan 2020
Research Intern & Part-time Researcher, Microsoft Research New England
Intern (Jun–Oct 2019) then part-time researcher (Oct 2019–Jan 2020) on Project AutoML. Developed a novel AutoML approach later published at NeurIPS.
Jun -- Oct 2018
Research Intern, Microsoft Research Redmond
Intern on Project Brainwave. Investigated novel arithmetic for training transformers and delivered the first transformer trained with MXINT, which later became NVFP on Blackwell GPUs. Filed 8 US patents.
Jun -- Oct 2017
Research Intern, Microsoft Research Cambridge
Intern on Project Sirius. Helped deliver a prototype of the Top of Rack switch.
2016 -- 2017
MPhil in Advanced Computer Science, University of Cambridge
Computer Laboratory.
2013 -- 2016
BEng in Electrical & Electronic Engineering, Imperial College London
Final years supervised by Prof. George Constantinides. Won the Willis Jackson Medal and Prize for academic performance. Final year project published at FPT 2016.

Research

My research sits at the intersection of hardware, algorithms, and security in machine learning, with work regularly appearing at NeurIPS, ICML, and ICLR, and at leading security venues (USENIX, S&P, SaTML), hardware/systems venues (MLSys, ISCA), and journals including Nature.

On the efficient AI side, I work on algorithmic designs spanning quantization, pruning, and neural architecture search, as well as building hardware accelerators. Our open-source framework MASE enables cross-stack ML acceleration research; PLENA is the first fully open AI accelerator system, covering full RTL, simulator, and compilers. On the AI security side, I study adversarial robustness, architectural backdoors, and model collapse in recursively trained systems.

I serve as Area Chair for ICLR, ICML, NeurIPS, and CVPR.

Awards

Initiatives

Spatial ML Center CaRAML Group Imperial AI Network AIxSIM

Teaching

I teach two courses at Imperial College London (2023–2025):

Advanced Deep Learning Systems
ELEC70109 / EE9-AML3-10
Advanced Deep Learning Systems
 Information Processing
ELEC50009
Information Processing

Contact

The best way to reach me is email: a.zhao@imperial.ac.uk.

I am currently not taking new PhD students. I occasionally host visiting PhD students, but only when the research topic is a very strong match.

For student projects (MPhil, Part II/III, final year projects, summer internships, and similar): I only work with students from Imperial College London or the University of Cambridge — if you are from elsewhere, I am unlikely to reply. Due to capacity limits, day-to-day supervision comes from a PhD student or RA in the DeepWok Lab or the AIxSIM group, with me providing additional support. Please reach out directly to a member of these groups first and secure their agreement to supervise you before contacting me — I will not be able to take you on without a day-to-day supervisor already in place.