Data Scientist
Current- Test and evaluate computer vision machine learning models that detect and classify audio signatures- Revise and update data visualization pipeline to improve speed and visualization quality, saving 3 days of manualdata processing and visualization per quarter before critical stakeholder presentations- Construct a data pipeline, performing analysis with SciPy, Scikit-learn, and Statsmodels, and visualizations withMatplotlib and Seaborn, deployed with Docker, saving weeks of expensive classified data modeling and analysis- Utilize evolutionary computing to create mock machine learning models with specified metrics for Wizard of Oztesting to correlate user performance with model performance to guide future model development goals- Perform in-depth code reviews and adhere to software development best practices including Black and Rufflinting, MyPy static type checking, full codebase test coverage with PyTest, and Git version control
