Built a vector search tool that lets you visualize queries in real time

Prototyped and developed RAG interface in Atlas

Developed a domain-specific language for scalable dataset annotation and state management

Rearchitectured backend data model for core performance improvements and modular builds

Built full-stack features in Django and VueJS for telehealth web application.

Designed a workflow management system in Python for monitoring patient onboarding and experience.

Developed data engineering workflows with PySpark on EMR data.

Built model training and deployment pipelines with AzureML and MLflow.

Adapted a static analysis library to work with C++ projects as part of a CI/CD pipeline.

Developed SQL queries and PowerBI reports for tracking worker safety during pandemic.

Implemented an open-source Python package for multiview learning.

Developed novel random forest algorithm for estimating mutual information.

Built Python pipeline that detects and classifies different synapses in brain images.

Deployed web service that launches pipeline jobs in the cloud using AWS Batch and Docker.

Used MongoDB to store and format MRI scans; developed RESTful API to handle queries.