Senior SDET · AI & LLM Quality Engineering
Senior SDET, 10 years building test infrastructure where reliability is essential: airline payments, multitenant healthcare SaaS, fintech, financial market data.
For the past few years my focus is testing AI powered features: LLM evaluation harnesses, RAG retrieval testing, golden dataset regression, agentic system testing. I build the frameworks and runners, and wire evaluation into CI/CD.
→ Full background, experience and competencies on mariusargatu.com/about
- AI / LLM testing: does the model answer faithfully, and can you prove it? faithfulness, answer relevancy, and hallucination scoring · RAG retrieval metrics (hit rate, MRR, precision/recall@k) · agentic multi turn and tool call testing
- Test architecture: the frameworks and runners under the tests. model based testing (xState) · property based testing (Schemathesis, Hypothesis, fast-check) · Pydantic schemas
- QARoom: a multitenant social platform built to demonstrate testability as an architectural property, using chaos engineering, contract testing, mutation testing, and model based and property based testing, all mapped to the boundary they defend.
- PayFlow: a payment system built by an AI agent from a frozen spec, zero hand written tests, guarded by a four layer verification pyramid (structural, behavioral, agent judgment, mutation). 73.1% mutation kill rate.
- Atlas: a testable broadband support agent (LangGraph + MCP), the runnable reference system for the "Evals Are Checks, Not Tests" series.
- TemporalMutate: semantic mutation testing over Temporal workflows, where an agent hunts for blind spots in a payment workflow's test suite and every verdict comes from replaying recorded histories in milliseconds, with no live server.
- Metrics and the Lying Judge: Calibrate the LLM Judge
- The Golden Dataset: Building the Oracle You Test Against
- The Harness Is the Product: Models Are a Commodity
→ Read everything on mariusargatu.com/blog
- AI / LLM: DeepEval, RAGAS, Langfuse, Pydantic
- Languages: Python, TypeScript
- Test: Playwright, Pytest, Vitest
- API and contract: GraphQL, OpenAPI
- CI/CD and infra: GitHub Actions, Docker
“A test suite is a liability as much as an asset. Every test earns its place.”