MS Computer Science at NC State
I'm a software engineer completing my master's at NC State, where I study deep learning systems and distributed systems. I'm seeking full-time backend and applied AI/ML engineering roles.
New grad · May 2027
Explains why US air quality spikes, not just what the number is
A live app that turns AirNow monitor data, Open-Meteo weather, and NASA FIRMS fire hotspots into ranked explanations for local air quality events. Every explanation is grounded in this evidence and checked by a second model before it's shown.
Finds cracks in bridge concrete from drone photos
A custom U-Net with sliding-window inference over high-resolution UAV imagery, so thin cracks stay visible without blowing GPU memory. Overlapping tiles are blended with a Gaussian weight map; the current checkpoint adds squeeze-and-excitation and deep supervision.
0.730 Dice · 0.575 IoU · 0.739 recall · 0.721 precision
Drag to compare
Lets an agent monitor and interpret hyperparameter tuning in real-time
A decoupled HPO supervisor. The search runs on Optuna's TPE sampler, the FastAPI backend suggests hyperparameters in under 20ms and prunes weak trials, and an MCP server gives IDE agents read-only access to the run database; the optimization is never blocked by or dependent on the LLM.
| Suggestion latency | < 20 ms |
| Pruning + health flags | stalled / OOM |
| Backend | SQLite WAL |
| Agent access | read-only MCP |
Training never waits on the LLM; the agent only reads what you ask it to read.
Model compression tradeoff study for solar-powered ocean buoys
An edge deep-compression study for classifying marine microplastics on solar-powered IoT buoy cameras: quantization and pruning under simulated Raspberry Pi 4B constraints, measured against a LoRaWAN payload budget.
| Variant | Acc | Size | Latency |
|---|---|---|---|
| FP32 baseline | 98.91% | 5.98 MB | 370 ms |
| QAT INT8 | 96.10% | 4.24 MB | 347 ms |
| INT8 + prune 70% | 91.60% | 1.52 MB | 337 ms |
Trading off 7.3 accuracy points for -74.6% payload and self-sustaining solar power.
Prometheus Group
Full-stack developer · C#/.NET, React
Full-stack development in C#/.NET and React, plus the automated testing framework that cut regression time by 40%.
Fidelity Investments
Software engineer intern · Java, Spring Boot, Azure
Java Spring Boot services and Azure Service Bus pipelines for 401(k) transaction processing.
UNC Charlotte
Undergraduate researcher · C++, HPC
Adapted Microsoft's ALEX learned index to dynamic graph workloads in C++; OpenMP parallelization for up to 20x speedup.
Fidelity Investments
Software engineer intern · Java, Spring Boot, AWS
Extended Fidelity Bloom's Round Up feature with percentage and custom dollar amounts; built user-preference REST APIs on AWS Lambda.
M.S. Computer Science, NC State · ML/AI concentration · GPA 3.78
B.S. Computer Science, UNC Charlotte · Software Engineering · Magna Cum Laude · GPA 3.85
February 24, 2026
What I learned from a year of research on ALEX and other learned index structures.