- 🎓 I'm a Computer Science and Mathematics major at Vanderbilt University (Class of 2027)
- 🤖 Passionate about building impactful AI/ML tools, scalable web apps, and solving real-world problems with code
- 🌱 Constantly learning — currently focused on MLOps, distributed systems, and system design
- ⚽ Fun fact: I love watching soccer, telling stories, and creating things that make people’s lives easier
- 📫 Email: [email protected]
🔗 Fall AI Studio Repo
📌 Pinned at the top of my GitHub profile
Includes:
- ✅ Overview, goals, and methods
- 📈 Visualizations and results
- 🧪 Sample datasets
- 📘 Jupyter notebooks & reproducibility guide
- 💡 Individual contributions
Here are some of my favorite and most representative projects:
A Python library to retrieve and analyze SEC EDGAR filings like 10-K and 10-Q for public companies.
- 🧰 Python, requests, EDGAR API
- 🔍 Supports ticker-to-CIK lookup, financial metrics, and date-filtered filings
- 💾 Optional caching, CLI/interactive mode, and robust documentation
- ✅ Built with clean, modular design and tested endpoints
A CS course assistant trained on class notes and Piazza posts using RAG and GPT-4.
- 🔧 Built with LangChain, Pinecone, Flask, React
- 📚 Used by 200+ students at Vanderbilt CS department
- 📊 Contains visual diagrams, model tuning docs, and sample questions
➡️ More projects on my GitHub
✅ All project repos are public and contain clear titles and documentation.
Languages: Java, Python, C/C++, JavaScript, TypeScript, SQL, Go, Bash
Frameworks/Tools: React, Flask, Node.js, Tailwind, Docker, Kubernetes, AWS
Data/AI: Pandas, NumPy, scikit-learn, Matplotlib, LangChain, Pinecone
DevOps: GitHub Actions, CI/CD, VS Code, Jupyter
I actively follow and engage with open-source projects that align with my work in AI/ML, backend systems, and MLOps. Some notable repositories I follow and learn from include:
- langchain-ai/langchain: A powerful framework for building context-aware LLM applications. I use LangChain in my RAG-based chatbot projects.
- mlflow/mlflow: A leading platform for managing the end-to-end machine learning lifecycle. I'm exploring experiment tracking and model deployment with MLflow.
- iterative/dvc: Git-like version control for ML pipelines and data. I'm incorporating DVC in my AI Studio project to ensure reproducibility.
- pydantic/pydantic: A fast, type-safe data validation library used in many of my Python and FastAPI projects.
These projects inspire my work and reflect the kind of engineering practices I strive to follow — reproducibility, clarity, and modular design.