QA Automation & SDET
Python automation, Appium, Sauce Labs, regression strategy, release validation, logs, defect triage, and cross-team QA planning.
QA Automation · Data Science · Production-minded ML
I build reliable software, test systems, and data products with an engineering-first mindset.
I’m Tetiana Kravchuk, a Software QA Engineer with 9+ years of automation and release-quality experience, currently completing a Master’s in Data Science at Boston University. My work connects careful testing, Python automation, data validation, and machine learning.
Focused on roles where quality, data, and ML meet.
My strongest fit is QA Automation / SDET, Data Quality, ML QA, AI testing, and applied data science roles where reliability, clear metrics, and production behavior matter.
Data Science & ML
Model evaluation, supervised learning, feature analysis, experiment tracking, data quality, and responsible use of predictive systems. Includes an interactive flashcard study lab.
Data Products
Flagship work on World Publishing Houses, a publishing intelligence platform focused on metadata quality, translation transparency, and provenance. WPH connects my QA discipline with data product thinking.
Featured work
Projects selected to show technical depth, business thinking, and the bridge from software quality to data science.
Flagship product project
World Publishing Houses
A global publishing intelligence platform designed to track publishers, books, translators, translation paths, rights signals, and country-level literary ecosystems. The project combines data modeling, QA, product design, and responsible metadata transparency.
ML capstone + study tool
Residential Property Value Prediction
Machine learning project using property features to predict assessed values, comparing linear regression, random forest, and gradient boosting with RMSE, MAE, and R². The Data Science page also includes flashcards for interview prep.
Professional impact
QA Metrics & Automation Impact
Evidence-based QA story using bug reporting, ticket closure, test case creation, release support, automation contributions, and triage improvements.
Working principle
Reliable AI and data products start with trustworthy inputs, clear assumptions, tested workflows, and honest evaluation. My QA background gives me a practical lens for building ML systems that are not only accurate in notebooks, but understandable and testable in real product conditions.