I'm a Senior Software Engineer specializing in software engineering in test. I've spent over a decade in legal technology: I started in data migration, moved into QA as an SDET in 2020, and now I keep myself at the leading edge of AI by building agentic systems for testing.
To stay at the cutting edge of AI in testing, I design multi-agent pipelines for test generation: an orchestrator that hands work to test-writer, evaluator, and code-review agents, so a work item ends up as reviewed, CI-passing tests with very little of my time in the loop.
I've built Playwright end-to-end and API test suites from the ground up, and spent a lot of time on the isolation patterns that keep a large suite fast and trustworthy when it runs in parallel.
Day to day that means .NET/C#, Python, and TypeScript; running agents on Docker, Kubernetes, and AWS; and building agentic tooling with both frontier and local models.