I am a software engineer and AI-focused Computer Information Systems student at the University of South Carolina, building production-oriented systems across backend engineering, applied machine learning, research software, and full-stack product development.
My work spans Java backend engineering, AI-driven application development, synthetic data generation, PyTorch-based perception models, WebGL2 research tooling, and developer-facing software for academic and enterprise environments. I focus on building systems that are technically sound, measurable, secure, and usable by real stakeholders.
I approach engineering through a product lens: define the user problem, design the system boundary, ship a working solution, measure performance, and iterate with feedback. My current work emphasizes AI/ML systems, full-stack applications, cloud-native tooling, and secure software delivery.
|
|
| Domain | Proficiency | Details |
|---|---|---|
| Applied Machine Learning | Advanced | Model development, evaluation workflows, synthetic data validation, and applied AI prototyping |
| Computer Vision | Advanced | EO/IR camera modeling, obstacle recognition, maritime perception, and adverse-condition evaluation |
| Deep Learning | Advanced | PyTorch-based model development for perception and navigation-oriented research systems |
| Generative AI | Advanced | Amazon Bedrock integration, AI-driven solution design, and enterprise use-case prototyping |
| Data Science | Advanced | NumPy, Pandas, Matplotlib, simulation analysis, sensor evaluation, and model performance review |
| AI Research Engineering | Advanced | Research software development, experiment support, reproducible demos, and stakeholder-facing validation |
| AI Product Engineering | Advanced | Translating client and research needs into usable, testable, engineering-driven AI systems |
AI-Driven Civil Sector Solution
Enterprise AI solution developed in a 10-week startup accelerator environment for a civil sector client challenge. The project focused on backend engineering, Amazon Bedrock integration, synthetic dataset generation, AI validation, and final solution delivery for senior leadership review.
| Category | Details |
|---|---|
| Stack | Java, Amazon Bedrock, AWS, Synthetic Data, AI Evaluation |
| Scale | 10-week accelerator environment with enterprise stakeholder review |
| Performance | Validated AI workflows using synthetic datasets where real client data was unavailable |
| Security | Designed with enterprise cloud, data handling, and client-sensitive workflow constraints |
| Impact | Supported final AI solution presentation to senior leadership |
The system emphasized practical AI delivery under real-world constraints: incomplete data access, short execution timelines, stakeholder expectations, and the need for measurable technical validation. The engineering work centered on building a Java backend, integrating foundation model capabilities through Amazon Bedrock, and constructing synthetic datasets to support training, testing, and evaluation.
Reliable Perception for Unmanned Maritime Systems
AI research system supporting a US Navy-sponsored engineering team focused on maritime obstacle recognition, sensor evaluation, and perception reliability under adverse environmental conditions.
| Category | Details |
|---|---|
| Stack | Python, PyTorch, Computer Vision, Simulation, EO/IR Modeling |
| Scale | 10+ simulations, 15+ engineers, 5+ adverse operating conditions |
| Performance | Improved obstacle detection evaluation across fog, night, rain, and other degraded environments |
| Security | Research aligned with mission-critical perception reliability and maritime autonomy constraints |
| Impact | Developed AI-enabled camera models outperforming human operators in maritime obstacle recognition |
This project focused on the engineering and evaluation of AI-enabled perception models for unmanned maritime systems. Work included simulation execution, sensor evaluation, adverse-condition testing, and PyTorch-based EO/IR camera model development to improve recognition and navigation performance.
IPyNiiVue
Research software project porting the WebGL2-based NiiVue neuroimaging visualization tool into a Jupyter Notebook environment using Python, enabling interactive notebook-based demonstrations and research workflows.
| Category | Details |
|---|---|
| Stack | Python, Jupyter, WebGL2, NiiVue, Research Software |
| Scale | 10+ demonstrations showcasing full tool capabilities |
| Performance | Improved accessibility of browser-based visualization workflows inside notebooks |
| Security | Developed within academic research software constraints and reproducible workflow expectations |
| Impact | Enabled notebook-native neuroimaging visualization for research and demonstration use cases |
| Repository | GitHub |
IPyNiiVue was designed to bridge interactive neuroimaging visualization with notebook-based research workflows. The project required translating WebGL2-driven capabilities into Python-accessible demonstrations, identifying software issues, optimizing usability, and incorporating feedback from academic professionals.
Teaching Assistant Programming Support System
Educational software and programming-support initiative for students in web development and introductory programming courses at the University of South Carolina.
| Category | Details |
|---|---|
| Stack | JavaScript, HTML, CSS, Programming Fundamentals, Web Development |
| Scale | One-on-one tutoring, group sessions, supplemental practice material, peer collaboration |
| Performance | Improved student support through targeted examples, practice problems, and coding review |
| Security | Reinforced secure, correct, and maintainable beginner programming practices |
| Impact | Supported undergraduate learning across programming and web development coursework |
The work emphasized practical instruction, debugging support, curriculum reinforcement, and development of supplemental materials. It required communicating technical concepts clearly while helping students build durable programming fundamentals.
Jun. 2026 - Present · Charleston, SC
Engineered AI-driven software for a civil sector client challenge within a 10-week startup accelerator environment, combining backend development, cloud AI integration, and synthetic data validation.
Scope of Work
- Engineered a Java backend for an AI-enabled civil sector solution.
- Integrated Amazon Bedrock into application workflows.
- Generated and validated synthetic datasets for training and evaluation.
- Supported testing where real client data was unavailable.
- Prepared solution outputs for presentation to senior leadership.
Aug. 2025 - May 2026 · Columbia, SC
Supported a US Navy-sponsored engineering research team focused on reliable perception, maritime autonomy, sensor evaluation, and adverse-condition obstacle recognition.
Scope of Work
- Executed 10+ simulations and sensor evaluations.
- Supported a research team of 15+ engineers.
- Evaluated obstacle detection across fog, night, rain, and other adverse conditions.
- Developed PyTorch-based EO/IR camera models.
- Improved maritime obstacle recognition and navigation performance.
Jan. 2025 - Aug. 2025 · Columbia, SC
Led development of IPyNiiVue, a Python and Jupyter-based research software project porting WebGL2 neuroimaging visualization capabilities into notebook workflows.
Scope of Work
- Led development of IPyNiiVue.
- Ported the WebGL2-based NiiVue tool into a Jupyter Notebook environment.
- Built 10+ demos showcasing tool capabilities.
- Collaborated with academic professionals on software issues.
- Optimized performance and implemented user feedback.
Oct. 2023 - May 2025 · Columbia, SC
Supported students in web development and introductory programming through tutoring, group study sessions, practice material development, and coding examples.
Scope of Work
- Provided one-on-one tutoring for programming and web development students.
- Supported group study sessions.
- Co-developed supplemental practice problems.
- Created coding examples for instructional use.
- Collaborated with undergraduate and graduate peers on student support.
| Recognition | Details |
|---|---|
| EY USC Case Competition 2026 | 1st Place |
| GCC University Case Competition 2025 | 2nd Place |
| Capstone Scholar | University of South Carolina honors distinction |
| Magellan Journey | Research and academic distinction |
| President’s List | Academic excellence recognition |
| Dean’s List | Academic excellence recognition |
| Dean’s Scholar | Academic excellence recognition |
| CFA Remarkable Futures | Scholarship and professional development recognition |
Learning:
- Advanced software engineering patterns
- Applied AI systems
- Secure cloud architecture
- Machine learning model evaluation
Building:
- AI-driven backend systems
- Full-stack engineering projects
- Research software tooling
- Developer-focused portfolio infrastructure
Exploring:
- Generative AI application design
- Computer vision for autonomous systems
- Cloud-native AI workflows
- Scalable product engineering
Open To:
- Software engineering internships
- AI / ML engineering roles
- Full-stack development opportunities
- Open source collaboration
- Research engineering workEngineering reliable software, applied AI systems, and product-grade technical solutions with measurable impact.