Work

In my current role, I work on homeowners insurance pricing models and the tooling around model development. Most of my modeling work has focused on production pricing models built on large-scale policy data. I process 10M+ policy records with SQL and PySpark in AWS SageMaker, engineer features from internal and third-party data, and use methods like GBM, LASSO, hierarchical clustering, interaction discovery, and GLM ensemble modeling to improve risk segmentation.

A lot of my recent work has also been about making the modeling workflow more reproducible. I refactored notebook-based workflows into modular Python packages and helped automate training, validation, and experiment tracking with SageMaker Pipelines and MLflow. This has made the work easier to rerun, test, and compare across model iterations.

I also build reusable Python libraries for model development. That includes GitLab CI/CD, automated tests, code quality checks, pre-commit hooks, JFrog package publishing, and Snyk dependency scanning. More recently, I implemented a FastMCP server that exposes custom Python tools so AI agents can retrieve and analyze feature-selection outputs during model development.

On the data engineering side, I build PySpark ETL pipelines with SageMaker Processing Jobs to ingest and transform production insurance records from an enterprise data lake. This part of the work has made me more interested in the full path from raw data to modeling pipeline to production-ready tools.

During my internship, I protyped homeowners insurance rating models using GLM and GBM models with Python and AWS SageMaker. During this internship, I learned the importance of interpretable model, which can be preferred over model optimized soley on predictibility. I also learned different ways to handle missinge values and how to work with large-scale datasets.

I led the administrative team as a Sergeant-in-Charge, overseeing the unit’s adminsitrative processes, and supporting day-to-day logistical and operational needs.

I also graduated Air Assault School, which is one of the most memorable experiences of my life. I still remember the first time I attempted the 12 mile ruck march as the initial qualifier for the school, I thought that I was making a mistake (12 mile ruck march is the final test at the Air Assault School where you carry a 45lb rucksack along with a rifle and have to march for 12 miles within 3 hours). After training everyday, I successfully accomplished all the required tasks and earned the Air Assault badge. To this day, I remember this event and think that any overwhelming barriers I encounter can be overcome with dedication and hardwork.