About
Hi! I’m Aryan, a Computer Science student at UT Dallas working across AI engineering, data science, and full-stack development. I enjoy building projects where those overlap, like a transit app with its own routing engine or a model that grades every shot from an NBA season.
Right now, I’m an AI Engineer Intern at Innowhyte (opens in new tab), working on an agentic AI project, and an undergraduate researcher in Dr. Alexander Michels’ spatial data science group (opens in new tab), studying gaps in healthcare access. Previously, I spent a year on the UT Dallas IT support desk helping students, faculty, and staff.
In my free time, I’m usually playing , hanging out with my friends, watching films (opens in new tab), or reading a book from my ever-growing reading list. Currently, I’m reading Urban Creatures (opens in new tab) by Sarah Gray.
Experience
Sept 2026 to Present
Spatial Data Science Researcher
UT Dallas
Studying healthcare access gaps in Dr. Alexander Michels’ group using population and facility data. Implementing place-based spatial accessibility measures modeled on the PySAL access package, including floating catchment area and gravity models, building on PostGIS work from LineFinder.
- Python
- PostGIS
- spatial analysis
Summer 2026 to Present
AI Engineer Intern
Innowhyte (opens in new tab) (Remote)
Built a full-stack conversational data analysis app that answers natural-language questions across multiple CSVs with text and charts. Designed an LLM planning pipeline that validates model-generated plans before deterministic Pandas execution, with a regression test suite. Now contributing to a live agentic AI project.
- Python
- FastAPI
- Next.js
- Pandas
- OpenAI API
- Docker
July 2025 to Aug 2026
OIT Support Desk Analyst
UT Dallas
Supported students, faculty, and staff across phone, email, chat, and remote channels, troubleshooting AWS remote access, Duo, Teams, PeopleSoft, Azure, and hardware and software issues.
- AWS
- Azure
- JIRA
- TeamDynamix
Projects
LineFinder
Mobile-first DART transit navigator with a custom RAPTOR-style routing engine, versioned GTFS schedule ingestion, walking-aware trip planning, and transfer-risk ranking, backed by 1.9M+ stop-time records in PostGIS.
- TypeScript
- Next.js
- Fastify
- PostgreSQL/PostGIS
- Redis
- Docker
Multi-CSV AI Data Assistant
Upload multiple CSVs and ask questions in plain English. The LLM produces a validated analysis plan and Pandas does all the math, so model-generated code is never executed. Handles multi-hop joins while preventing fanout double-counting, and rejects unverified joins.
- Python
- FastAPI
- Pydantic
- Pandas
- OpenAI API
- Next.js
- Docker
NBA Shot Quality Model
ML pipeline on 128K NBA shots predicting make probability, benchmarking five model families and explaining the model with SHAP. Deployed as an interactive dashboard with a shot predictor and an out-of-sample player shot-making leaderboard.
- Python
- LightGBM
- XGBoost
- SHAP
- Next.js
- Vercel
Credit Default Risk Benchmark
Tabular ML benchmark for credit default prediction with model comparison, threshold analysis, calibration, and SHAP explainability.
- Python
- scikit-learn
- LightGBM
- XGBoost
- SHAP
Skills
- Languages
- Python
- TypeScript
- JavaScript
- Java
- C++
- SQL
- R
- HTML/CSS
- AI & ML
- PyTorch
- scikit-learn
- XGBoost
- LightGBM
- SHAP
- OpenAI API
- Anthropic API
- LangChain
- LangGraph
- LangSmith
- RAG
- structured outputs
- Data
- Pandas
- NumPy
- Plotly
- Jupyter
- PostgreSQL/PostGIS
- spatial accessibility analysis
- Web & Backend
- FastAPI
- Pydantic
- Next.js
- React
- Fastify
- Redis
- MapLibre
- Tools & Infra
- Docker
- Git
- GitHub Actions
- Vercel
- pytest
- Vitest
- pnpm
- Linux
- AWS
- Azure
- Claude Code
- Codex