Google PMLE — Professional ML Engineer Practice Exam

A scenario-style practice exam for the Google Cloud Professional Machine Learning Engineer (PMLE). Draws 50 questions per attempt from a blueprint-weighted pool (Scaling prototypes ~21% · Serving & scaling ~20% · Pipelines & orchestration ~18% · Data & model management ~15% · Low-code AI ~13% · Monitoring ~13%), with a 120-minute soft timer. Google does not publish an official PMLE pass mark, so the 70% here is a READINESS BENCHMARK, not the real cut. Original 5-choice 'which Vertex AI / GCP service fits' MCQs with worked explanations and a per-section weak-area breakdown. Pairs with the six PMLE decks. Progress saves in your browser — no login.

Multiple choice, one question at a time. You can jump around and change answers before submitting. After you submit you'll see your score and can review every question you missed with an explanation. Progress is saved in this browser — no login needed.