//hi guys!
CS + Applied Statistics at Purdue. I'm interested in machine learning, software development, and overall making cool stuff :D
const chen = {
studying: ["CS", "Applied Stats"],
hobbies: ["cooking", "table tennis"],
sleep: false
};My work spans machine learning, software development, and applied statistics. I'm drawn to problems where probabilistic modeling and data-driven decisions meet the real world, whether that's building machine learning systems at scale or pursuing quantitative research in markets.
I'm a CS + Applied Statistics student at Purdue, where I concentrate in machine learning and intelligence and gravitate toward the probabilistic and statistical side of both majors. Previously, I spent the spring at Rolls-Royce working on a synthetic data framework for turbofan telemetry that lets PHM researchers train models without ITAR-restricted engine data. I built a GPU-accelerated conditional diffusion pipeline with transformer-based masked denoisers and inpainting-style sampling, and I also experimented with LoRA fine-tuning and synthetic data evaluation using MMD and domain-classifier metrics. Lately, I have been exploring LLM reliability evaluation at AbbVie, and this August I'll be joining Jane Street's INSIGHT program on the Trading & Research track.
Technical Skills
- Python
- R
- C
- C++
- Java
- JavaScript
- TypeScript
- C#
- SQL
- Bash
- x86 Assembly
- HTML/CSS
- Ellmer
- Vitals
- PyTorch
- TensorFlow
- Keras
- Scikit-learn
- NumPy
- Pandas
- Matplotlib
- FastAPI
- Flask
- React
- Node.js
- SQLAlchemy
- OpenCV
- ROS
- PostgreSQL
- PostGIS
- MongoDB
- REST APIs
- Git
- Linux
- Docker
- AWS
- Gazebo
- GDB
- Valgrind
- Lex/Yacc