Milena Cylińska

Senior QA Automation Lead and consultant with 10+ years of experience building reliable, scalable test automation and CI/CD quality gates for production systems – including AI-enabled products. She specializes in evaluating AI system reliability in production, particularly RAG and agent-based architectures, building evaluation layers (rather than assumptions) that assess outputs for accuracy, relevance, safety, and tone. Her work has helped teams cut testing time by ~80% and move to Continuous Deployment. She partners with engineering and product teams to build tooling developers actually use, ensuring systems perform reliably in real-world workflows – not just against specifications.