Available for Summer 2026 Opportunities

<E.Justice/>

ML Researcher | LLM Inference Optimization | vLLM

Hi, I'm Ethan Justice - a Computer Science student at the University of Michigan researching KV-cache optimization and multi-agent LLM systems. Building production-grade ML infrastructure on HPC clusters.

8+
Years Coding
5
Internships
11+
Projects
LLMs
Research Focus
Scroll

02. Experience Timeline

From ML research to enterprise software engineering, building production systems at scale.

Machine Learning Researcher

University of Michigan - RobustNet Lab
research

Transitioning state-of-the-art KV-caching research into production-compatible infrastructure for vLLM and LMCache ecosystem.

Nov 2025 - Present(1 mo)Ann Arbor, Michigan

AI Engineering Intern

PersistOS, Inc.
internship

Second non-founding engineer building core infrastructure for an agentic memory platform.

Aug 2025 - Nov 2025(3 mos)San Francisco Bay Area

Software Engineering Intern

Little Caesars Pizza
internship

Developed and improved critical internal systems for operational efficiency across 5,000+ franchise locations.

May 2025 - Aug 2025(3 mos)Detroit, Michigan

Research Assistant

University of Michigan - Interactive Sensing and Computing Lab
research

Created embedded systems for real-time user activity identification using machine learning.

Sep 2024 - Dec 2024(3 mos)Ann Arbor, Michigan

Flight Systems Developer

M-Fly Aero Design
project-team

Developed software for autonomous plane navigation and control surfaces.

Sep 2023 - Sep 2024(1 yr)Ann Arbor, Michigan

Software Development Intern

United Wholesale Mortgage
internship

Re-engineered internal employee rewards platform used by 750+ team leads.

May 2024 - Aug 2024(3 mos)Pontiac, Michigan

Lead Programmer

Hartland Robotics - FRC Team 3536
project-team

Led software development for competitive FIRST Robotics Competition team, programming autonomous and teleoperated robot control systems.

Jun 2019 - Jun 2023(4 yrs)Hartland, Michigan

03. Work & Projects

From ML research to hackathon wins, building solutions across the stack.

Filter by skill: |
Type
Category

Efficient Heterogeneous LLM Multi-Agent Debate Framework

projectFeatured
Aug 2025 - Dec 2025
University of Michigan

Resource-efficient Multi-Agent System reducing inference costs for complex reasoning tasks by 40%.

  • HPC Deployment on Great Lakes cluster with Slurm job scheduling
  • 40% reduction in total FLOPs via confidence-based gating mechanism
  • Factory Pattern for modular model backend switching between vLLM and HuggingFace
  • Identified Syntactic Determinism failure modes in token-confidence calibration
PythonPyTorchHuggingFacevLLMSlurmLlama-3DeepSeekMathstral

Information Digest

projectFeatured
Aug 2025 - Aug 2025

Agentic information retrieval pipeline with Infrastructure-as-Code and CI/CD automation.

  • Automated infrastructure lifecycle using Terraform and GitHub Actions
  • Comprehensive Pytest suites before deploying to GCP Cloud Run
  • Real-time search pipeline with LangChain and SerpAPI
  • LLM agent autonomously decomposes queries and synthesizes answers
  • Strongly-typed REST interface with deterministic JSON outputs
PythonLangChainFastAPIDockerTerraformGCP Cloud RunGitHub ActionsSerpAPI

Machine Learning Researcher

research
Nov 2025 - Present
University of Michigan - RobustNet Lab
Ann Arbor, Michigan hybrid

Transitioning state-of-the-art KV-caching research into production-compatible infrastructure for vLLM and LMCache ecosystem.

  • Productionizing research from 'Compute Or Load KV Cache? Why Not Both?' paper
  • Porting logic from legacy codebase to current vLLM and LMCache main branches
  • Enabling bidirectional KV prefill to reduce Time-to-First-Token (TTFT)
  • Optimizing GPU memory transfer overhead on Great Lakes HPC (A100/H100 clusters)

AI Engineering Intern

internship
Aug 2025 - Nov 2025
PersistOS, Inc.
San Francisco Bay Area remote

Second non-founding engineer building core infrastructure for an agentic memory platform.

  • Architected real-time Multimodal RAG pipeline using GCS and Redis
  • Enabled sub-second voice-to-voice agent interactions
  • Engineered semantic caching layer via Convex - 99% reduction in API response times
  • Built 'LLM-as-a-Judge' testing suite for agent memory evaluation

Software Engineering Intern

internship
May 2025 - Aug 2025
Little Caesars Pizza
Detroit, Michigan hybrid

Developed and improved critical internal systems for operational efficiency across 5,000+ franchise locations.

  • Architected C# .NET microservice with REST API for SMS automation via Twilio
  • Single-handedly implemented complete CI/CD pipeline in Azure DevOps
  • Created batch-processing API achieving 90% reduction in developer time
  • Built franchise store hours compliance tracker for company-wide initiative

Interview Bot Pro

project
Feb 2025 - Mar 2025
University of Michigan

MacOS application for AI-powered interview practice with speech prosody analysis.

  • Tailored questions based on user experiences and target job requirements
  • Dynamic follow-up questions based on previous answers
  • STAR method structure analysis and content grading
  • Voice prosody analysis using Random Forest ML trained on MIT interview dataset
  • Job fit analysis with skill parsing and requirement matching
PythonGoogle GeminiRandom Forest MLSpeech Prosody Analysis

Ribbet - MHacks Project

project
Oct 2024 - Oct 2024

Cross-platform social media app with betting mechanics built during MHacks hackathon.

  • MERN Stack architecture for cross-platform mobile development
  • Complete CRUD functionality for user and post data
  • Social media features: profiles, feeds, and betting mechanisms
MongoDBExpress.jsReact NativeNode.js

The Situation Room - Cal Hacks

project
Oct 2024 - Oct 2024

Unity game simulating de-escalation scenarios with AI-driven dialogue analysis.

  • Interactive dialogue with dynamic character responses
  • Google Gemini integration for dialogue content analysis
  • Hume AI for real-time sentiment analysis
  • Python backend server for API integration
UnityC#PythonGoogle GeminiHume AI

Research Assistant

research
Sep 2024 - Dec 2024
University of Michigan - Interactive Sensing and Computing Lab
Ann Arbor, Michigan on-site

Created embedded systems for real-time user activity identification using machine learning.

  • Built embedded system on Orange Pi for activity level identification
  • Leveraged Llama 3 model for sensor data analysis
  • Implemented multithreading for performance optimization
  • Strategic task routing to high-performance CPU cores

Inner Voice AI

project
Jul 2024 - Jul 2024

Conversational AI therapist that won 1st place at Stemist Hacks hackathon.

1st Place - Stemist Hacks
  • 1st Place Winner at Stemist Hacks hackathon
  • OpenAI API for natural conversational flow
  • Hume AI for real-time sentiment analysis
  • Firebase for user sessions and conversation history
PythonFlaskOpenAI APIHume AIFirebaseSQL

Software Development Intern

internship
May 2024 - Aug 2024
United Wholesale Mortgage
Pontiac, Michigan on-site

Re-engineered internal employee rewards platform used by 750+ team leads.

  • 20% increase in monthly active users after platform modernization
  • Led requirement gathering with Employee Engagement stakeholders
  • Managed backend operations for 50,000+ entry dataset
  • Implemented automated testing protocols for high availability

Thread Library

class project
Jan 2024 - Present
EECS 482 - Operating Systems

User-level threading library with context switching

  • Context switching
  • Thread scheduling
  • Synchronization primitives
C++

Pager

class project
Jan 2024 - Present
EECS 482 - Operating Systems

Virtual memory pager with demand paging

  • Page fault handling
  • Memory management
  • Swap space
C++

File System

class project
Jan 2024 - Present
EECS 482 - Operating Systems

Multi-threaded network file server

  • File system design
  • Network protocols
  • Concurrency
C++

Multi-Agent Debate Framework

class project
Jan 2024 - Present
EECS 498 - Machine Learning Research

Efficient heterogeneous LLM multi-agent debate for factual reasoning

  • 40% FLOP reduction
  • Confidence-based gating
  • HPC deployment
PythonPyTorchvLLM

Pipeline Simulator

class project
Jan 2024 - Present
EECS 370 - Computer Organization

5-stage MIPS pipeline simulator with hazard handling

  • Data hazards
  • Control hazards
  • Forwarding
C

Maze Solver

class project
Jan 2024 - Present
EECS 281 - Data Structures and Algorithms

Puzzle solver using BFS/DFS with custom data structures

  • Search algorithms
  • Stack/Queue implementation
C++

Priority Queue

class project
Jan 2024 - Present
EECS 281 - Data Structures and Algorithms

Binary and pairing heap implementations

  • Heap operations
  • Amortized analysis
C++

Database Query Optimizer

class project
Jan 2024 - Present
EECS 281 - Data Structures and Algorithms

SQL-like query processor with indexing

  • B-tree indexing
  • Query optimization
C++

TSP Solver

class project
Jan 2024 - Present
EECS 281 - Data Structures and Algorithms

Traveling Salesman Problem with MST heuristics

  • MST algorithms
  • Branch and bound
  • Approximation
C++

Flight Systems Developer

project-team
Sep 2023 - Sep 2024
M-Fly Aero Design
Ann Arbor, Michigan on-site

Developed software for autonomous plane navigation and control surfaces.

  • Implemented 3DVFH* algorithm for obstacle avoidance
  • Used ROS and MAVLink for plane control
  • Integrated remote ID for aircraft location tracking

MAT-5 Autonomous Plane

project
Aug 2023 - Jul 2024
M-Fly Aero Design

Flight systems software for autonomous plane navigation using 3DVFH* obstacle avoidance.

  • 3DVFH* algorithm for dynamic obstacle avoidance
  • Autonomous path following
  • Remote ID for receiving locations of other aircraft
  • ROS and MAVLink for control surface integration
PythonROSMAVLink3DVFH*

Reaper - FRC 2023

project
Jan 2023 - Jun 2023

Competition robot with differential swerve drive for FRC Charged Up game.

  • Motion profiling for precise velocity and position control
  • Differential swerve drive chassis control
  • PID tuning with data collection and analysis
  • Autonomous pathing with time axis integration
C++WPILibDifferential Swerve Drive

Blade - FRC 2022

project
Jan 2022 - Dec 2022

Swerve drive robot for FRC Rapid React with autonomous shooting up to 30ft.

  • Autonomous shooting with calculated launch angle and velocity
  • State-based control for robot operations
  • Time-of-flight sensor integration with Arduino
  • Absolute arm angle calculation using gravity vector
C++ArduinoWPILibSwerve Drive

NavPod

project
Jan 2020 - Jun 2023

Embedded system for precise robot position tracking using sensor fusion.

  • Optical flow sensor for translational movement tracking
  • IMU for rotational movement tracking
  • Custom sensor fusion algorithm for position determination
  • I2C communication with serial output over USB
ArduinoC++I2COptical Flow SensorIMU

Raptor - FRC 2020

project
Jan 2020 - Dec 2021

Competition robot with autonomous turret tracking and Hermite spline pathing.

  • Hermite spline autonomous pathing
  • NavPod integration for precise localization
  • Auto-aiming turret based on robot position
  • Computer vision with GRIP pipeline for ball detection
C++PythonRaspberry PiOpenCVWPILib

Lead Programmer

project-team
Jun 2019 - Jun 2023
Hartland Robotics - FRC Team 3536
Hartland, Michigan on-site

Led software development for competitive FIRST Robotics Competition team, programming autonomous and teleoperated robot control systems.

  • Developed autonomous routines using path planning and odometry
  • Implemented vision processing for game piece detection
  • Programmed drivetrain, arm, and intake subsystems in Java
  • Mentored younger students in programming and engineering practices

04. Education

Coursework, projects, and academic achievements at Michigan Engineering.

EDU-UMICH

University of Michigan

Bachelor of Science in Engineering in Computer Science

Aug 2023 - May 2026Ann Arbor, Michigan

Dean's ListUniversity HonorsMichigander EV and Mobility ScholarUndergraduate Research Opportunity Program
Activities:M-Fly Aero DesignMichigan HackersClaude Builder's Club
Coursework

05. Contact

Interested in collaborating or have an opportunity to discuss? Let's connect.

CONTACT-INFO

Get in Touch

ethanjus@umich.edu
Ann Arbor, Michigan
Connect
Available for Summer 2026 Opportunities
CONTACT-FORM

Send a Message