Rahman Doost-Mohammady

Rahman Doost-Mohammady

(he/him)

Assistant Research Professor

Rice University

Professional Summary

I work at the intersection of computer systems and wireless networking — building programmable, intelligent infrastructure for 5G/6G and Open RAN. A common thread across my projects is algorithm and system design across FPGA, GPU, and CPU — spanning real-time massive MIMO baseband on commodity servers, many-antenna hardware platforms, and learning-driven schedulers. I am currently focused on virtualized Open RAN systems and ML-enabled RAN software design.
Download CV

Interests

Wireless Networking (5G/6G, Open RAN) Machine Learning for Wireless Reconfigurable Computing & Software-Defined Systems RAN Virtualization Large-scale MIMO Architectures AI-driven Resource Allocation

About

I am an Assistant Research Professor in the Department of Electrical and Computer Engineering at Rice University. My research is at the intersection of computer systems and wireless networking — building programmable, intelligent infrastructure for 5G/6G and Open RAN, with a focus on algorithm and system design across FPGA, GPU, and CPU. This spans software-defined massive MIMO baseband, scalable many-antenna platforms, virtualized RAN systems, and machine-learning-driven scheduling.

I currently lead ETHOS — a multi-dimensional approach to ML-enabled RAN software design (NTIA Public Wireless Supply Chain Innovation Fund, 2024–2028) — and co-lead Houdini, an open-access multi-band software-defined radio platform (NSF CNS-2346550), and 3DML, a community platform for ML-driven wireless research (NSF CCRI, 2020–2026). Previously, I co-led RENEW (NSF PAWR, 2018–2023) — an open-source software-defined massive MIMO platform deployed on the POWDER testbed.

Selected Publications

  • Many-antenna massive MIMO platforms and real-time baseband. From hardware architectures that scale to hundreds of coherent radio chains, to software-only baseband processing on commodity servers: Agora (ACM CoNEXT'20), ArgosV3 (ACM MobiCom'17).

  • AI-driven scheduling and RAN slicing. Real-time ML and slice-aware schedulers for massive MIMO: Helix (ACM CoNEXT'24), Deep RL Resource Scheduler (IEEE TMLCN'23).

  • ML-based massive MIMO detection. Sampling-based detectors that approach ML accuracy at far lower complexity: Annealed Langevin Detector (IEEE TWC'22).

  • Virtualized Open RAN systems. Measurement and design for 5G O-RAN on commodity infrastructure: ETHOS (ACM WiNTECH'25).

  • Wireless physical-layer security. PHY techniques that protect legitimate transmissions against eavesdroppers: M3A (ACM MobiCom'23).

I am always happy to discuss collaborations — feel free to reach out.

All Publications
Zongshen Wu, Rahman Doost-Mohammady, Ashutosh Sabharwal (2025). ETHOS: Demystifying Performance, Energy, and Computational Efficiency in Virtualized 5G O-RAN Networks. ACM WiNTECH 2025.
PDF Source Document DOI
Qing An, Divyanshu Pandey, Rahman Doost-Mohammady, Ashutosh Sabharwal, Srinivas Shakkottai (2024). Helix: A RAN Slicing Based Scheduling Framework for Massive MIMO Networks. Proc. ACM Netw. (CoNEXT 2024).
PDF Source Document DOI
Zhecun Liu, Keerthi Priya Dasala, Di Mu, Rahman Doost-Mohammady, Edward W. Knightly (2023). M3A: Multipath Multicarrier Misinformation to Adversaries. ACM MobiCom 2023.
PDF Source Document DOI
Qing An, Chris Dick, Santiago Segarra, Ashutosh Sabharwal, Rahman Doost-Mohammady (2023). A Deep Reinforcement Learning-Based Resource Scheduler for Massive MIMO Networks. IEEE TMLCN.
PDF DOI
Nicolas Zilberstein, Chris Dick, Rahman Doost-Mohammady, Ashutosh Sabharwal, Santiago Segarra (2022). Annealed Langevin Dynamics for Massive MIMO Detection. IEEE TWC.
See all
Recent & Upcoming Talks
Recent News

Qing An defends PhD thesis

Qing An successfully defended his PhD thesis and has joined Apple. Congratulations Dr. An!

Serving as Local Chair for ACM MobiHoc 2025

I will serve as Local Chair for ACM MobiHoc 2025 — the ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing.