I build high performance systems for modern data centers, with a focus on AI and ML workloads and their efficiency at scale. I am comfortable moving across different problems, but my core experience is in systems software. You can find me at the Computer Laboratory, where I am visiting Andrew Moore at the University of Cambridge.
I spent about two years at Huawei working on Compute Express Link (CXL) across QEMU and the Linux kernel, exploring how memory systems should evolve for modern data centers. More recently, I have been focusing on AI and ML workloads and the systems challenges they introduce. I am interested in optimizing these workloads at scale across networking, memory, and runtime layers, with a growing emphasis on energy efficiency alongside performance.
My interests broadly center on computer systems for data centers, especially where real systems meet emerging workloads. I enjoy technical discussions and early stage ideas, and I am always open to exchanging thoughts.
I received my PhD from Queen Mary University of London, advised by Gianni Antichi and Brent Stephens (Utah / Google), see my PhD dissertation. I was more than fortunate to work with both Gianni and Brent; beyond their technical depth, they each have distinct styles that strongly shaped how I think about systems and research.
Before starting my PhD, I was initially an Intern, and later a Research Assistant at NUS, advised by Djordje Jevdjic, working on memory management for data-center applications. I also spent three months at EPFL, studying the feasibility of using virtualization to improve the availability of electrical grid controllers, advised by Jean-Yves Le Boudec. Btw, Lausanne is beautiful, make sure you pay a visit.
I completed my undergraduate and master’s studies at IUST (Iran), working with Mohsen Sharifi, where I spent two years as a student in his laboratory.
Selected Publications (all pubs)
Enabling Fast Networking in the Public Cloud
A. Sanaee, V. Jabrayilov, I. Marinos, F. Shahinfar, D. Saxena, G. Antichi, and K. Kaffes
ACM ASPLOS 26, Code Paper
IPA: Inference Pipeline Adaptation to Achieve High Accuracy and Cost-Efficiency
S. Ghafouri, K. Razavi, M. Salmani, A. Sanaee, T. Botran, L. Wang, J. Doyle, P. Jamshidi
ICPE 25
Scalable and Effective Page-table and TLB Management on NUMA Systems
B. Gao, Q. Kang, H. Tee, K. Chu, A. Sanaee, D. Jevdjic
USENIX ATC 24, Paper, Talk, Podcast
Backdraft: a Lossless Virtual Switch that Prevents the Slow Receiver Problem
A. Sanaee, F. Shahinfar, G. Antichi, B. Stephens
USENIX NSDI 22, Paper, Talk, Code, Podcast
Morpheus: Domain-Specific Run Time Optimization for Software Data Planes
S. Miano, A. Sanaee, G. Retravi, G. Antichi
ACM ASPLOS 22, Paper, Talk, Code, Podcast
Workshops
Reconciling High Accuracy, Cost-Efficiency, and Low Latency of Inference Serving
M. Salmani, S. Ghafouri, A. Sanaee, K. Razavi, M. Mühlhäuser, J. Doyle, P. Jamshidi, M. Sharifi
MLSys Workshop @ EuroSys 23, Paper, Talk
Teaching
I enjoy mentoring students and working closely on open-ended projects.
- Undergraduate & Postgraduate Final Project Supervision (20 students) — Fall ’24 & Summer ’25
- Undergraduate & Postgraduate Final Project Supervision (10 students) — Fall ’23 & Summer ’24
- Compilers — Spring ’24 (Teaching Fellow)
- Distributed Systems — Spring ’24 (Teaching Fellow)
Service
Previous Mentees
- Farbod Shahinfar — now PhD student at Politecnico di Milano
- Mohammad Siavashi — MSc from IUST, now PhD student at KTH Royal Institute of Technology
- Master’s thesis: Development of a Page Table Aware Scheduler. Paper
- Mehran Salmani — MSc from IUST, now PhD student at Technische Universität Ilmenau
- Master’s thesis: A Mechanism for Auto-Configuration of ML Inference Services
Some thoughts
Occasional notes, opinions, and unfinished ideas:
- Hosts can get congested too — here for more
- TCP seems to be hampering innovation
- The process of conducting research is slow
- Fair comparison requires proper artifacts (even though it’s hard)
- One way to become more interesting today: add AI/ML before any noun.
Start from AI/ML Systems 🙂 (21/12/2023)
Useful Graduate School Stuff
- How to write a good Computer Systems Dissertation?
- Avoid fixed schedules with many meetings
- My take on NUS and Nanyang Universities
- Graduate school advice
- Be stupid
- Life Lessons from the First Half-Century of My Career
Linux kernel stuff
Random Stuff
- So you want to review?
- Try rehab, but soon you’ll know you should have taken shoulder surgery at t=0!
- Shoulder Labral Repair
- Share Your Arm Dislocation or Rotator Cuff Tear Experience
- No hello
Company interview rejections (since 2018)
Listed mostly as a reminder that this is normal:
- Microsoft — 1× R1, 1× R2
- NVIDIA — R2
- Meta — 2× R1
- Google — R1
- D. E. Shaw — R2
- XTX Markets — R2
- TikTok — R4