Tech Stack: Python, XGBoost, Google BigQuery, SQL

Expert’s cases:

1. Pipeline design, implementation & deployment for data processes

2. SFTP Server setup with Cloud Back-end to aid transferal of client data

3. Setup monitoring for lag between API calls and actionable events

4. Revamp of autocampaigns utilizing up to date ML development and engineering strategies, leveraging distributed computing for data preprocessing, and kubeflow for DAGs

5. Development of stringent MLOps pipeline to allow for expansion of client facing ML features

6. Deploying Open Source LLMs with exposed endpoints for streaming text

7. Development of Pipelines to leverage LLMs for automated SQL Query Generation

8. Developed predictive models, applied data mining methodologies, and used salient visualizations based on client needs (selected projects in following bullet points)

9. Unsupervised Clustering of wastewater treatment data to find patterns in dissolved oxygen levels, an important measure of treatment efficacy

10. Building models on clinical patient data to predict amount of protein CD138, a metric utilized in the diagnosis of immune born cancers