Engineering / Research / Applied ML

Selected work.

Systems I've helped build, methods I've worked with, and how I approach evaluation.

01

Research systems

Human–AI research platform

Turning experimental requirements into a platform for research and structured data collection.

Research engineeringPythonEmpiricaValidationFebruary 2026 — present
02

Applied machine learning

Adapting protein language models

Training and evaluation pipelines for comparing adaptation methods across repeated experiments.

PyTorchESM-2LoRASlurmFebruary 2026 — present
03

Software engineering

CAMP — Campus asset management

A team-built platform for authenticated campus resource workflows, with contributions to backend APIs and integration testing.

ReactExpressMongoDBMocha / ChaiFall 2024
04

Multilingual NLP

Named-entity recognition in Hinglish

Fine-tuned multilingual encoders and separately evaluated zero-shot language-model baselines on Hindi–English code-mixed text.

PyTorchTransformersmBERTXLM-RoBERTaFall 2024

Additional projects

Applied data science / Fall 2025

Salary prediction

A workflow on 742 cleaned Glassdoor job listings, combining PyCaret model comparison, XGBoost, SHAP interpretation, MLflow tracking, and Streamlit.

Source code ↗

Statistical modeling / Spring 2025

Community crime data analysis

Regression and single-holdout evaluation across 1,994 U.S. communities, with a Streamlit app for descriptive exploration. Associations are observational, not causal.

Source code ↗