Serhat Arslan
 |
I was a Ph.D. candidate at Stanford University in the Department of Electrical Engineering since Autumn 2018 and have graduated in Spring 2024. After Stanford, I started working in the industry to develop the ML-optimized networking systems. My PhD research studied how to optimize the transport layer to minimize tail latency both at the end hosts and the network in data centers. I have also worked on extracting the most effective telemetry from different types of networks to make them more controllable, i.e. bringing controllability to cellular networks with a systems approach. Advisor: Nick McKeown and Sachin Katti Email: 12 serhat dot arslan at gmail dot com Connect:
|
Education
Ph.D., Electrical Engineering, Stanford University, June 2024
M.S., Electrical Engineering, Stanford University, June 2020
B.S., Electrical and Electronics Engineering, Koç University, June 2016
Work Experience
Nvidia Corporation Senior Host System Architect, GPU Networking (Remote USA, 2025-Present)
I work on protocol and algorithm evaluations under the Networking Software and Systems Architecture team.
Intel Corporation Senior AI Network and Transport Layer Modeling Engineer (Remote USA, 2024-2025)
Silicon Product Architect under the Networking Product & Platform Architecture team.
I developed the behavioral model of the AI Connectivity solutions for large-scale performance evaluations.
Google LLC Software Engineering Intern (Bay Area, Summer 2021)
I worked with the Congestion Control Team for Google Core Infrastructure Group.
We worked on developing an extremely low latency congestion control algorithm using recent technologies in switching.
Google LLC Software Engineering Intern (Bay Area, Summer 2020)
I worked with the Network Data Analytics Team for Google Cloud.
My job was to develop performance models to improve visibility into the network using telemetry and machine learning.
Vodafone Converged Packet Network Senior Specialist (Istanbul, 2016-2018)
I was responsible for the Internet domain of national network for mobile Vodafone customers.
My work included internet router migrations and development of new tools (using Python) to get automated state and inventory reports from the network.
Patents
Network Congestion Control In Sub-Round Trip Time
Serhat Arslan, Yuliang Li, Gautam Kumar, Nandita Dukkipati
US Patent App. 18/136,551
Publications
 |
NanoTransport: A Low-Latency, Programmable Transport Layer for NICs |
 |
The nanoPU: A Nanosecond Network Stack for Datacenters |
 |
Enabling the Reflex Plane with the nanoPU |
 |
Bolt: Sub-RTT Congestion Control for Ultra-Low Latency |
 |
SFC: Near-Source Congestion Signaling and Flow Control |
 |
Switches Know the Exact Amount of Congestion |
 |
Moving Beyond Proxy Signals for Datacenter Congestion Control |
 |
Updating the Theory of Buffer Sizing |
 |
Green With Envy: Unfair Congestion Control Algorithms Can Be More Energy Efficients |
 |
d-Cellular Trust-Free Connectivity in Decentralized Cellular Networks |
 |
Trust-free Service Measurement and Payments for Decentralized Cellular Networks |
 |
Using Google Search Trends to Estimate Global Patterns in Learning |
Academic Service
Technical Program Committee (TPC) Member, ACM Internet Measurement Conference (IMC), 2026
Technical Program Committee (TPC) Member, IEEE International Conference on Computer Communications (INFOCOM), 2026
Reviewer, IEEE/ACM Transactions on Networking, 2024 - Present
The Networking Channel Panel: How to give an interesting talk for a SIGCOMM/NSDI or similar audience? [video]
Shadow Program Committee (PC) Member, EuroSys 2021
Tutorial Recording: Introduction to NS3 (Network Simulator 3)
Homa Transport Protocol (Montazeri et al.) implementation on NS3 (Network Simulator 3)
Teaching
CS 244 Advanced Topics in Networking Teaching Assistant (Stanford University, Spring 2021)
A graduate course in computer networks. It explores pros and cons of the principles and design decisions which underly the Internet, and gives some thought to how we can make the Internet better in future. The class is based on discussion about the research papers read by students before every lecture. Usually, leading researches in the field are invited to facilitate discussion on their papers.
CS 144 Introduction to Computer Networking Teaching Assistant (Stanford University, Autumn 2020)
An intensive laboratory class that teaches the basic principles of computer networks, such as packet switching, layering, encapsulation and protocols. Duties of the teaching staff include holding office hours, responding student question via Piazza, and grading lab submissions and exams.
CS Bridge Section Leader (Istanbul, 2016 and 2019)
A non-profit international program that offers a two-week, intensive residential summer course for 16 and 17 year old high school students.
The course is based on Stanford’s CS106A Programming Methodology (in Java) course. My duty was to help students with their coding projects during lab hours and conduct discussion sections where we review and discuss topics covered in lectures. In addition, I translated most of the content, i.e. projects and exercises, into Turkish on the course page