Ansel K. Erol

Atlanta, GA

I’m a BS/MS student at Georgia Tech (graduating May 2026) studying Computer Science, with a focus on the challenges of deploying real-time, high-throughput software systems at scale — for analytical, machine learning, and transaction processing workloads. I am also a Graduate Teaching Assistant for CS 3600: Artificial Intelligence.

My research at the Systems for Scalable Intelligence (SCAI) Lab (advised by Dr. Divya Mahajan) centers on scaling ML inference on constrained and distributed systems — efficient MoE model serving and edge computing on satellites. I have presented first-author work at MLSys ‘25 and ‘26 and at the CRNCH Summit ‘26, and received the President’s Undergraduate Research Award (PURA).

On the industry side, I interned at Google (Mountain View, Summer 2025), where I optimized gRPC networking for a low-latency C++ inference system in private ML ad infrastructure. Before that, I interned at Travelers Insurance on cloud data infrastructure. I am an incoming Forward Deployed Software Engineer at Baseten (San Francisco, starting June 2026).

I am also a Board Member and former Finance Director of People for PSEO, a Minnesota non-profit advocating for dual-enrollment students.

Outside of work and research, I enjoy classical music, travel, pastry, and poetry — visit my passions page to learn more.

News

Mar 01, 2026	Thrilled to share two updates: I’ll be joining Baseten as a Forward Deployed Software Engineer this June, and EarthSight has been accepted to MLSys 2026 — my first first-author conference paper!
Feb 12, 2026	Presented EarthSight at the CRNCH Summit 2026, and it has been accepted to appear at the 2026 Annual Conference on Machine Learning and Systems (MLSys 2026)!
Dec 01, 2025	Gave an invited talk on Graph Theory at Izmir University of Economics (December 2025).
May 10, 2025	Presented EarthSight as first author at the MLSys ‘25 Young Professional’s Symposium in Santa Clara, CA.
May 01, 2025	Started my Software Engineer internship at Google in Mountain View, CA, working on low-latency C++ ML inference infrastructure.

Selected Publications

EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence

A. K. Erol, S. Lee, and D. Mahajan

In Annual Conference on Machine Learning and Systems (MLSys), 2026

To appear. Also presented at GT Undergraduate Research Symposium (Apr 2025), MLSys Young Professional’s Symposium (May 2025), and CRNCH Summit (Feb 2026)

First Author Bib

Presented as first author at MLSys ’25 and ’26

@inproceedings{erol2025earthsight,
  title = {EarthSight: A Distributed Framework for Low-Latency Satellite Intelligence},
  author = {Erol, A. K. and Lee, S. and Mahajan, D.},
  booktitle = {Annual Conference on Machine Learning and Systems (MLSys)},
  year = {2026},
  note = {To appear. Also presented at GT Undergraduate Research Symposium (Apr 2025), MLSys Young Professional's Symposium (May 2025), and CRNCH Summit (Feb 2026)},
}

Efficient Scheduling for Low-latency Satellite Intelligence

A. K. Erol

Georgia Institute of Technology, 2025

First Author Bib

Solo author

@mastersthesis{erol2025scheduling,
  title = {Efficient Scheduling for Low-latency Satellite Intelligence},
  author = {Erol, A. K.},
  school = {Georgia Institute of Technology},
  year = {2025},
}

Trust by Design: Skill Profiles for Transparent, Cost-Aware LLM Routing

M. Okamoto, A. K. Erol, and G. Matlin

In 8th Annual Conference on Machine Learning and Systems, Young Professional’s Symposium, 2025

Bib

@inproceedings{okamoto2025trust,
  title = {Trust by Design: Skill Profiles for Transparent, Cost-Aware {LLM} Routing},
  author = {Okamoto, M. and Erol, A. K. and Matlin, G.},
  booktitle = {8th Annual Conference on Machine Learning and Systems, Young Professional's Symposium},
  year = {2025},
}

A Holistic Approach to Workforce Scheduling and Routing

C. K. Manalp, A. K. Erol, K. Erol, and 1 more author

2024

Bib