|

Master's Data Science Student at UT Dallas. I'm very passionate about using data to solve real-world problems. I also love building things and helping people.
Logan Margabandu

About

I love learning new things and expanding my repertoire so one day I'll be able to make a difference in the world. As an undergraduate, I authored a peer-reviewed IEEE conference publication as the primary author. I love applying Machine Learning to solve real-world problems. Outside of coding, I sharpen my strategic thinking through chess and bring that analytical mindset to building impactful applications.

Work Experience

Federal Reserve Bank of Dallas

Federal Reserve Bank of Dallas
Current

Oct 2025 - Present
High Performance Computing Software Engineer Intern
Click to see details

High Performance Computing Software Engineer Intern

Oct 2025 - Present

  • Maintain and utilize BigTex, the Federal Reserve's largest HPC cluster, for large-scale macroeconomic simulations, data-intensive research, and performance optimization across parallel compute environments.
  • Apply deep learning and machine learning to macroeconomic and financial models, optimizing and translating research code (Fortran, C++, Python) for efficiency, scalability, and reproducibility across HPC environments.
Python
Machine Learning
LLMs
Research
National Science Foundation

National Science Foundation

May 2025 - Aug 2025
Machine Learning Research Intern
Click to see details

Machine Learning Research Intern

May 2025 - Aug 2025

  • Refined and continued to develop an interactive Oracle app integrating Design of Experiments techniques with LLMs, achieving more than 90% test case response accuracy and reducing manual validation time by 60% compared to baseline QA workflows.
  • Designed and executed 50+ structured experiments across 7+ combinatorial testing strategies, generating empirical insights that reduce QA costs in machine learning systems by up to 40% and accelerate validation and adoption in safety-critical, regulatory-sensitive industries.
  • Authored a peer-reviewed IEEE conference publication as sole author, positioning the research to shape next-generation ML testing standards and improve software reliability and regulatory compliance in industry.
Python
Machine Learning
LLMs
Research
Fellows Consulting Group

Fellows Consulting Group

Jan 2025 - May 2025
Software Engineer Intern
Click to see details

Software Engineer Intern

Jan 2025 - May 2025

  • Built and deployed a containerized full-stack application that reduced deployment time by 40% and maintained 99.9% uptime, ensuring faster go-to-market and stronger client satisfaction.
  • Designed and fine-tuned a DoE Oracle LLM (Llama 3.2) that cut manual test-case validation effort by 60%, enabling consultants to reallocate hours to higher-value client work and reduce QA overhead.
  • Increased model accuracy by 35% across 10K+ test scenarios by integrating multiple ML frameworks, directly improving product reliability and lowering the risk of costly production defects.
Python
Docker
LLMs
FastAPI
UT Dallas Office of Technology Experience and Innovation

UT Dallas Office of Technology Experience and Innovation

Jul 2024 - May 2025
Information Technology Support Specialist
Click to see details

Information Technology Support Specialist

Jan 2025 - May 2025

  • Increased automation efficiency by 40% by optimizing 10+ bots, making them more robust & sustainable.
  • Manage and resolve 40+ complex technical issues monthly through TeamDynamix, ensuring a 95%+ satisfaction rate.
  • Deliver expert technical assistance for NetID setups, Wi-Fi troubleshooting, DUO MFA, malware scanning, and SailPoint password resets with a 98% first-contact resolution.

Computer Lab Assistant

Jul 2024 - Jan 2025

  • Provided technical support and assistance to students and faculty in computer lab environments.
IT Support
Automation
TeamDynamix

Publications

A Design of Experiments Oracle LLM for Research-Grounded Combinatorial Testing

Sep 2025
2025 25th International Conference on Software Quality, Reliability, and Security Companion (QRS Companion)

Skills

Programming Languages

Frontend

Backend

DevOps

Machine Learning

Others

My Projects

Check out my
latest work

I've worked on a variety of projects, from simple websites to complex web applications. Here are a few of my favorites.

DOE Oracle LLM

DOE Oracle LLM

A specialized AI system using Retrieval-Augmented Generation (RAG) to answer questions about combinatorial testing based exclusively on research papers. Features a custom fine-tuned model with citation support.

Python
React
Flask
RAG
LLMs
AVANCE Dallas Grant Finder

AVANCE Dallas Grant Finder

A bilingual platform that simplifies grant discovery and application tracking, helping organizations find and apply for funding opportunities more efficiently.

React
FastAPI
PostgreSQL
Python
Scrapy
Hackathons

I like building things

I participated in my first hackathons and it was so fun to come together and build something with like-minded individuals.

  • HackUTD 2025 Logo

    HackUTD 2025

    Richardson, TX

    The Datacenter Technician's Copilot. An AI-powered system that streamlines data center operations with voice agents, vision analysis, and autonomous ticket management.
    HackUTD 2025
    HackUTD 2025
    HackUTD 2025
    HackUTD 2025
    HackUTD 2025
    HackUTD 2025
    HackUTD 2025
  • HackUTA 2025 Logo

    HackUTA 2025

    3rd Overall

    Arlington, TX

    An AI-powered health companion that creates a living digital twin to unify your health data, predict changes, and turn everyday tracking into real-time intelligence.
    HackUTA 2025
    HackUTA 2025
    HackUTA 2025
    HackUTA 2025
Contact

Get in Touch

Want to chat? Just shoot me an email