Amir Noohi
PhD Candidate
University of Edinburgh
Education
PhD, Computer Science
The University of Edinburgh, Edinburgh, UK
Advisor: Dr. Antonio Barbalace & Dr. Boris Grot
Master of Science, Computer Science
Isfahan University of Technology, Isfahan, Iran
Advisor: Dr. Massoud Reza Hashemi
GPA: 4/4 - 19.01/20 (Ranked 1st)
Bachelor of Science, Computer Engineering
Isfahan University of Technology, Isfahan, Iran
Advisor: Dr. Elham Mahmoud Zadeh
GPA: 3.8/4 - 18.51/20 (Ranked 1st)
Publications
Amir Noohi, Antonio Barbalace. "TENURE: Residency Leases for Tiered LLM KV Caches." ACM Symposium on Cloud Computing (SoCC), 2026. ACM artifact badges: Available, Functional, Reproduced.
Amir Noohi, Mostafa Derispour, Rodrigo Caetano de Oliveira Rocha, Antonio Barbalace, Artemiy Margaritov. "SagePTE: Co-Locating Guest and Host PTEs to Accelerate Virtual Memory Translation." IEEE/ACM International Symposium on Microarchitecture (MICRO), 2026. Distinguished Paper Award. ACM artifact badges: Available, Functional, Reproduced.
Amir Noohi, Bita Asoodeh, Antonio Barbalace. "Towards a solution to the management scaling paradox in distributed LLM inference." Proceedings of the 6th Workshop on Machine Learning and Systems (EuroMLSys), 2026.
Amir Noohi, Saba Ebrahimi, Mostafa Derispour, Antonio Barbalace. "NTSM: OS-Level Memory Middleware for Scaling AI Without Boundaries." ACM/IFIP International Middleware Conference (Middleware), 2026.
Amir Noohi, Mostafa Derispour, Antonio Barbalace. "RMAI: Rethinking Memory for AI (Inference) In-Kernel Remote Shared Memory as a Software Alternative to CXL." Proceedings of the 5th Workshop on Machine Learning and Systems (EuroMLSys), 2025.
Abbas Khater, Amir Noohi, Massoud Reza Hashemi, Zeinab Zali. "An NFV-Based Framework for Autonomous Deployment of New Protocols in SDN Networks." IEEE Access, 2024.
Research Interests
Computer Architecture
CPU Architecture
Systems for ML
Operating Systems
Distributed Systems
HW/SW Co-design
Virtualization
Experience
CPU Researcher, Huawei Technologies Research & Development (UK) Ltd
Researching CPU architecture optimizations for AI agentic workloads.
CPU Architect, Huawei Technologies Research & Development (UK) Ltd
Leveraged the 128-bit extended PTEs developed during my internship to accelerate virtualized address translation.
CPU Architect, Huawei Technologies Research & Development (UK) Ltd
Extended Linux kernel page table entries (Level 3 entries) to 128-bit and modified QEMU to support this feature.
CEO & Founder, HIGHHOST
Founded and operated a comprehensive web hosting company offering dedicated servers, virtual private servers (VPS), shared hosting, cPanel hosting, reseller hosting, and domain registration services.
Research Assistant, Isfahan University of Technology
Designed and implemented a novel NFV-based framework for autonomous protocol deployment in SDN networks.
Technical Product Manager, IAI Core Center
Led the development of a patient-nurse communication platform for Iran Zamin Clinic, consisting of Android and web applications.
Cloud Engineer, Isfahan University of Technology
Infrastructure: Architected and deployed a production-grade private cloud serving 100+ physical servers across 5 data center racks.
Software Developer, Isfahan University of Technology
Developed the backend for Jinaro project using Laravel (PHP), implementing RESTful APIs and database architecture.
Teaching
University of Edinburgh
Lead Teaching Assistant — Operating Systems
Lead Teaching Assistant — Programming for Data Science at Scale
Teaching Assistant — Introduction to Computer Systems
Lead Teaching Assistant — Operating Systems
Lead Teaching Assistant — Programming for Data Science at Scale
Lead Teaching Assistant — Operating Systems
Teaching Assistant — Extreme Computing
Teaching Assistant — Operating Systems
Sharif University of Technology
Lecturer — Database
Teaching Assistant — Data Mining
Teaching Assistant — Advanced Software Engineering
Isfahan University of Technology
Lead Teaching Assistant — Computer Networks
Lead Teaching Assistant — Computer Networks
Lead Teaching Assistant — Advanced Programming
Teaching Assistant — Fundamental Programming
Teaching Assistant — Computer Security
Teaching Assistant — Computer Networks
Lead Teaching Assistant — Advanced Programming
Teaching Assistant — Basic Programming
Lead Teaching Assistant — Advanced Programming
Teaching Assistant — Basic Programming
Teaching Assistant — Fundamental Programming
Teaching Assistant — Basic Programming
Teaching Assistant — Basic Programming
Teaching Assistant — Basic Programming
Teaching Assistant — Advanced Programming
Student Mentorship
Bita Asoodeh (MSc by Research, University of Edinburgh, Aug 2026 - Present) — Kernel-space KV cache sharing for distributed LLM inference
Hasan Alhussain (MSc, University of Edinburgh, Dec 2025 - Jun 2026) — Optimizing OS-level memory management for AI inference under memory pressure with CXL-based shared memory
Arsh Kumar (BSc, University of Edinburgh, Nov 2025 - May 2026) — Optimizing OS-level memory management for AI inference under memory pressure with CXL-based shared memory
Saba Ebrahimi (MSc, Shahid Beheshti University, Aug 2024 - Dec 2025) — Visiting intern at UoE working on thread migration project with Huawei
Mostafa Derispour (BSc, Isfahan University of Technology, Jul 2023 - Nov 2025) — Distributed shared memory for AI workloads and SagePTE extended page table architecture
Ali Farahani (BSc, Sharif University of Technology, Jan 2025 - May 2025) — Optimizing shuffle operations in distributed AI training through OS-level memory management, implementing zero-copy data movement and NUMA-aware buffer allocation to reduce inter-node communication overhead
Zhengyi Chen (UG Project, University of Edinburgh, Sep 2023 - Mar 2024) — Coherency and consistency of modern DSM in Linux kernel
Tom Blackburn (UG Project, University of Edinburgh, Sep 2023 - Jan 2024) — Comparison of user-space and kernel-space DSM
Mohsen Ghasemi (BSc, Sharif University of Technology, Sep 2023 - Dec 2023) — Workload characterization and performance analysis for Distributed Shared Memory (DSM) systems, profiling memory access patterns, page fault rates, and coherence protocol overhead across AI and HPC workloads
AmirHossein Barati (BSc, Sharif University of Technology, Jun 2023 - Aug 2023) — Design and implementation of kernel-level Distributed Shared Memory (DSM) subsystem, including page fault handlers, remote memory access protocols, and coherence mechanisms using RDMA for low-latency data transfer
Honors & Awards
Distinguished Paper Award — IEEE/ACM International Symposium on Microarchitecture (MICRO), 2026
Ph.D. Scholarship Award — School of Informatics, University of Edinburgh, 2023
Ranked 1st in M.Sc. — Isfahan University of Technology, 2021
Ranked 1st in B.Sc. — Isfahan University of Technology, 2019
Direct Admission to M.Sc. — Isfahan University of Technology, 2019
National Exceptional Talents Scholarship — Iran's National Foundation for Exceptional Talents, 2019
Top 1% in University Entrance Exam — Iranian National Exam, 2015
Physics Olympiad - Ranked 7th — National Physics Olympiad, 2014
Math Olympiad - Ranked 5th — National Math Olympiad, 2013
Talks & Service
"Q3 2026 Huawei Workshop" — Huawei Technologies Research & Development, Q3 2026
"Q2 2026 Huawei Workshop" — Huawei Technologies Research & Development, June 2026
"Towards a solution to the management scaling paradox in distributed LLM inference" — EuroMLSys 2026 Workshop, May 2026
"Q4 2025 Huawei Workshop" — Huawei Technologies Research & Development, December 2025
"RMAI: Rethinking Memory for AI Inference" — EuroMLSys 2025 Workshop, March 2025
"Q4 2024 Huawei Workshop" — Huawei Technologies Research & Development, December 2024
Student Volunteer, EuroSys 2026 (May 2026)
Artifact Evaluation Committee, EuroSys 2025 (Fall 2025)
Artifact Evaluation Committee, EuroSys 2025 (Spring 2025)
Shadow Program Committee, EuroSys 2025 (March 2025)
Skills
Languages: C/C++, Python, Rust, PHP, Java, JavaScript/TypeScript, Bash/Shell, SQL, Assembly (x86/ARM64)
Systems Programming: Linux Kernel Development, QEMU/KVM, Memory Management, Device Drivers
Virtualization & Cloud: KVM/QEMU, VMware vSphere/ESXi, Docker/Containers, OpenStack, Xen, Hyper-V
Databases: MySQL/MariaDB, PostgreSQL, MongoDB, Redis, SQLite
Networking: Wireshark, tcpdump, iptables/nftables, BGP/OSPF, SDN/OpenFlow, Mininet, DPDK, NS2/NS3
ML & Data Science: PyTorch, vLLM, Ray / Ray Serve, Hugging Face Transformers, DeepSpeed, NCCL, CUDA/cuDNN, LMCache, TensorFlow, Pandas/NumPy, Hadoop/Spark