Dimitrios Skarlatos profile photo

Dimitrios Skarlatos

Assistant Professor, Computer Science

  • Pittsburgh PA UNITED STATES

Dimitrios Skarlatos is redesigning AI data center infrastructure to improve energy efficiency.

Contact

Biography

Dimitrios Skarlatos’ research bridges computer architecture and operating systems focusing on performance, security, and scalability. His current work follows two central themes: uncovering security vulnerabilities and building defenses at the boundary between hardware and OS, and re-designing abstractions and interfaces between the two layers to improve performance and scalability.

Skarlatos is leading a groundbreaking project funded by CMU’s Wilton E. Scott Institute for Energy Innovation to redesign AI data center infrastructure. His team aims to improve energy efficiency by a factor of 20, using precise power control tools that don’t require rewriting existing AI software stacks.

Dimitrios Skarlatos earned a Ph.D. in computer science at the University of Illinois at Urbana-Champaign where he worked with Josep TorrellasOpens in new window in the i-acoma group. His alma mater is the Technical University of CreteOpens in new window in Greece, where he studied electronic and computer engineering. During his years in Crete, Skarlatos had the chance to work with Dionisios PnevmatikatosOpens in new window, Apostolos DollasOpens in new window, Ioannis PapaefstathiouOpens in new window, and Polyvios PratikakisOpens in new window.

Areas of Expertise

Data Center Design
Aritficial Intelligence
Systems
Security and Privacy
Computer Architecture

Media Appearances

Power Shift: How CMU Is Leading America’s Energy Evolution

CMU News  online

2025-07-11

From reimagining AI data centers to modernizing and securing the electric grid, CMU researchers are working on practical solutions to pressing challenges in how the U.S. produces, moves and secures energy.

“Our goal is to make tomorrow’s AI data centers drastically more energy-efficient through deep vertical integration of software and hardware," says Dimitrios Skarlatos, a computer science professor. "At CMU, we’re leading the charge in identifying the most promising research directions and working closely with industry for swift, practical technology transfer."

View More

Q&A with Dimitrios Skarlatos, visiting scientist at Facebook and assistant professor at Carnegie Mellon University

Meta Research  

2021-10-19

In this Q&A, Skarlatos shares his experience as a visiting scientist at Facebook, his motivation for taking a “prebattical,” the research projects he’s worked on, advice for academics considering a similar path, and more.

View More

Skarlatos' Inspired Research in Computer Architecture and Operating Systems Results in Outstanding Dissertation Award

University of Illinois Urbana-Champaign  online

2021-07-23

“Computing systems are undergoing a radical shift, propelled by stern security requirements and an unprecedented growth in data and users. This change has proven to be abstraction breaking,” Skarlatos said. “Current hardware and operating system abstractions were built at a time when we had minimal security threats, scarce compute and memory resources, and limited numbers of users. These assumptions are not representative of today’s computing landscape.

View More

Spotlight

1 min

Carnegie Mellon University, long known for its prowess in computer science and engineering, is now emerging as a key innovator within America’s energy landscape. As AI models grow more powerful, so too does their appetite for energy, straining an aging and outdated grid and prompting urgent questions about infrastructure, security and access. From reimagining AI data centers to modernizing and securing the electric grid, CMU researchers are working on practical solutions to pressing challenges in how the U.S. produces, moves and secures energy. Learn what CMU experts have to say about their Work That Matters.

Dimitrios SkarlatosZico KolterGranger MorganVyas SekarLarry Pileggi

Media

Social

Industry Expertise

Education/Learning
Computer/Network Security

Accomplishments

Google ML and Systems Junior Faculty Award

2026-07-01

The Google ML and Systems Junior Faculty Awards are given to 50 professors who are leading the analysis, design and implementation of efficient, scalable, secure and trustworthy computing systems. Their work crosses the technology stack, from algorithms to software and hardware, enabling machine learning and cloud computing at increasingly massive scale. The recipients were selected by a distinguished group of Google engineers and researchers.

IEEE TCCA CS Young Computer Architect Award

2025

Intel Outstanding Researcher Award

2025

Education

University of Illinois Urbana-Champaign

Ph.D.

Computer Science

University of Illinois Urbana-Champaign

M.S.

Computer Science

Technical University of Crete

B.S.

Electronic and Computer Engineering

Affiliations

  • Computer Architecture Lab at Carnegie Mellon (CALCM)
  • CyLab
  • Parallel Data Lab (PDL)

Patents

Secure cloud-based machine learning without sending original data to the cloud

US11568257

2019-05-20 Assigned to VMWARE, INC. reassignment VMWARE, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: BAPPANADU, ARAVIND, SIVARAMAN, HARI, SOUNDARARAJAN, VIJAYARAGHAVAN, SKARLATOS, DIMITRIOS, VU, LAN, KURKURE, UDAY

View more

Articles

Lithos: An operating system for efficient machine learning on gpus

Proceedings of the ACM SIGOPS 31st Symposium on Operating Systems Principles

Patrick H Coppock, Brian Zhang, Eliot H Solomon, Vasilis Kypriotis, Leon Yang, Bikash Sharma, Dan Schatzberg, Todd C Mowry, Dimitrios Skarlatos

2025-10-13

The rapid growth of machine learning (ML) has made GPUs indispensable in data centers and underscores the urgency of improving their efficiency. However, balancing diverse model demands with high utilization remains a fundamental challenge. Transparent, fine-grained GPU resource management that maximizes utilization, energy efficiency, and isolation requires an OS approach. This paper introduces LithOS, a first step towards a GPU OS.

View more

Rethinking computer architecture and operating system abstractions for good & evil

University of Illinois at Urbana-Champaign Thesis

2020

Computing systems are undergoing a radical shift, propelled by stern security requirements and an unprecedented growth in data and users. This change has proven to be abstraction breaking. Current hardware and Operating System (OS) abstractions were built at a time when we had minimal security threats, scarce compute and memory resources, and limited numbers of users. These assumptions are not representative of today’s computing landscape. On one hand, modern virtualization technologies have enabled the new cloud paradigms of serverless computing and microservices, which have in turn lead to the sharing of computing resources among hundreds of users. On the other hand, attacks such as Spectre and Meltdown have shown that current hardware is plagued by critical vulnerabilities. In this new era of computing, it is urgent that we question the existing abstractions of the OS and hardware layers and rethink their synergy from scratch. This thesis takes the first steps toward answering this question, while following two central themes:(a) uncovering security vulnerabilities and building defenses at the boundary between hardware and OS, and (b) re designing abstractions and interfaces between the two layers to improve performance and scalability.

View more