Cardinal HealthSr Data Engineer (AI/ML Analytics Team)
May. 2022 - Aug. 2022Ohio, United StatesAs a GCP Data Engineer on the AI/ML Team (Data & Analytics) at Cardinal Health, I engaged with business stakeholders to understand analysis goals and source data to be transformed into business insights. As a team leader, I took pride in ensuring the validity, and timeliness of the data I delivered. Moreover, I developed workflows for Exploratory Data Analysis (EDA profiling), validation, monitoring & establishing contingency plans across dynamic, cloud-based data pipelines. I ingested historical business data (demand, sales, inventory, logistics) and processed external factors (environmental, medical, social, & financial indicators) to transform and improve predictive models used for strategic planning. This work was performed remotely, in collaboration with a small team of data scientists organized to deliver incremental value via Scrum sprints. Within a few months, our team was able to improve demand forecasting models for kits sold from company distribution centers - reducing waste & increasing fill rates significantly. Primary technical tools included Google Cloud Platform - BigQuery (SQL)/GCS, Vertex AI, Dataflow & Cloud Composer (Airflow), and Python (pandas, jupyter). Most often, I excelled by performing intital EDA on raw data, developing ingestion methods into Warehouses/Lakes, and transformation/processing of data for cleaned data feature engineering & modeling input. I was also able to contrbute to ML/AI effort by comparatively evaluating different approaches (ARIMA vs PROPHET), and verifying data prep for maximum utilization in model algorithms. References Available & Below.