OptiNIC: A Resilient and Tail-Optimal RDMA NIC for Distributed ML Workloads
Ertza Warraich, Ali Imran, Annus Zulfiqar, Shay Vargaftik, Sonia Fahmy, Muhammad Shahbaz
Under submission
I build systems and architectures for large-scale AI. Currently building the next generation of cloud infrastructure for AI workloads.
I completed my Ph.D. in the Department of Computer Science at Purdue University, where I worked in the PurNET and NextGArch labs under the mentorship of Prof. Muhammad Shahbaz and Prof. Sonia Fahmy.
Earlier, I completed my B.Engg and M.S. at NUST, Pakistan, and spent several years in industry, beginning as a Malware Researcher and eventually advancing to the role of Assistant Manager.
My work spans systems, networking, and AI, with a focus on designing scalable and efficient infrastructure for the next generation of ML workloads.

Ertza Warraich, Ali Imran, Annus Zulfiqar, Shay Vargaftik, Sonia Fahmy, Muhammad Shahbaz
Under submission
Ertza Warraich, Ali Imran, Annus Zulfiqar, Shay Vargaftik, Sonia Fahmy, Muhammad Shahbaz
In IEEE Computer Architecture Letters (IEEE CAL 2025)
Virtual, Online. December 2025
Ertza Warraich, Omer Shabtai, Yonatan Piasetzky, Shay Vargaftik, Matty Kadosh, Lalith Suresh, Muhammad Shahbaz
In Proceedings of the 22nd USENIX Symposium on Networked Systems Design and Implementation (NSDI 2025)
Philadelphia, PA. April 2025
Kyungtae Kim, Taegyu Kim, Ertza Warraich, Byoungyoung Lee, Kevin Butler, Antonio Bianchi, Dave (Jing) Tian
In Proceedings of the 43rd IEEE Symposium on Security and Privacy (IEEE S&P 2022)
San Francisco, CA. May 2022
03.
I'm always open to discussing research collaborations, interesting problems in systems and AI infrastructure, or just saying hello.
Design inspired by Brittany Chiang & Devon Gifford