PRO
google
// professional machine learning engineer
PROFESSIONAL-MACHINE-LEARNING-ENGINEER
Prepare for Professional Machine Learning Engineer with curated, exam-aligned practice questions, explanations, and a study plan focused on real-exam outcomes.
339
questions
50
in exam
120m
duration
at a glance
What you get
PDF US$10.00Sub US$10/mopass Pass/fail (Google Cloud does not publish a numeric cut score)
Free practice questions are available without payment; anyone can start practicing at no cost.
access options
PDF bank or platform subscription?
Two separate purchases: a one-time PDF for Professional Machine Learning Engineer, or a monthly subscription for online practice and simulators across the platform. A subscription does not include the PDF download.
option / 01 · pdf file
Full question bank PDF
US$10.00· one-time
- Full question bank as a print-ready PDF
- Lifetime access to this exam only
- Domain-tagged questions with explanations
- Separate from online practice — buy once
option / 02 · subscription
All exams · practice & simulator
US$10.00· per month
- Practice & exam simulator on every bank
- All current and future exams included
- Personal analytics and retention tools
- Cancel anytime — no per-exam upsells
sample · 1 of 339Shuffle
See what's in the bank.
Collaborating within and across teams to manage data and modelsmedium
10 votes · last validated recently
You are building a real-time prediction engine that streams files which may contain Personally Identifiable Information (PII) to Google Cloud. You want to use the
Cloud Data Loss Prevention (DLP) API to scan the files. How should you ensure that the PII is not accessible by unauthorized individuals?
Cloud Data Loss Prevention (DLP) API to scan the files. How should you ensure that the PII is not accessible by unauthorized individuals?
A
Stream all files to Google Cloud, and then write the data to BigQuery. Periodically conduct a bulk scan of the table using the DLP API.
0%
B
Stream all files to Google Cloud, and write batches of the data to BigQuery. While the data is being written to BigQuery, conduct a bulk scan of the data using the DLP API.
40%
C
Create two buckets of data: Sensitive and Non-sensitive. Write all data to the Non-sensitive bucket. Periodically conduct a bulk scan of that bucket using the DLP API, and move the sensitive data to the Sensitive bucket.
0%
D
Create three buckets of data: Quarantine, Sensitive, and Non-sensitive. Write all data to the Quarantine bucket. Periodically conduct a bulk scan of that bucket using the DLP API, and move the data to either the Sensitive or Non-Sensitive bucket.
60%
04 · coverage
Exam domains
Architecting low-code ML solutions13%
53 q
Collaborating within and across teams to manage data and models14%
37 q
Scaling prototypes into ML models18%
107 q
Serving and scaling models20%
58 q
Automating and orchestrating ML pipelines21%
49 q
Monitoring ML solutions14%
35 q
community questionsview all →
Questions from the community
Top-voted approved contributions for this exam, reviewed before landing in the bank.
// top community questionsview all →
0.0 · 0 reviews
What candidates say
no reviews yet
related
You may also like
More exams based on your interests.
339 questions
PDF US$10.00 one-time·Sub US$10/mo
updated 7h ago·devco · cert
premiumgoogle cloud● updated 7h ago
Professional Machine Learning Engineer
Prepare for Professional Machine Learning Engineer with curated, exam-aligned practice questions, explanations, and a study plan focused on real-exam outcomes.
// OFFICIAL EXAM LOGISTICS
source · google cloud
// PASSING SCORE
750 / 1000· scaled
minimum to pass
75%of scale
// QUESTIONS
50official
// DURATION
120min
// EXAM FEE
200usd
// ITEM TYPES
multiple choice
multiple select
// questions
339in bank
// pass rate
92%self-reported
// last update
7h agoago
// add cadence · 12w
// downloadable pdf bank
Get the whole bank as a PDF
Every question tagged by domain, with a detailed explanation. Preview the first pages free — buy once for lifetime access to the full PDF.
339 questions
// what's inside
- 339 exam-style questions with verified answers
- Every question tagged by domain (6 domains covered)
- A detailed explanation / rationale for every question
// sample · 1 of 339
See what's in the bank.
#00e56e2b-bd36-49c9-bda7-a2534eb5deeeCollaborating within and across teams to manage data and modelsmedium
↑ +47· 8 comments· seen 1,284×
You are building a real-time prediction engine that streams files which may contain Personally Identifiable Information (PII) to Google Cloud. You want to use the
Cloud Data Loss Prevention (DLP) API to scan the files. How should you ensure that the PII is not accessible by unauthorized individuals?
Cloud Data Loss Prevention (DLP) API to scan the files. How should you ensure that the PII is not accessible by unauthorized individuals?
A
Stream all files to Google Cloud, and then write the data to BigQuery. Periodically conduct a bulk scan of the table using the DLP API.
0%B
Stream all files to Google Cloud, and write batches of the data to BigQuery. While the data is being written to BigQuery, conduct a bulk scan of the data using the DLP API.
40%C
Create two buckets of data: Sensitive and Non-sensitive. Write all data to the Non-sensitive bucket. Periodically conduct a bulk scan of that bucket using the DLP API, and move the sensitive data to the Sensitive bucket.
0%D
Create three buckets of data: Quarantine, Sensitive, and Non-sensitive. Write all data to the Quarantine bucket. Periodically conduct a bulk scan of that bucket using the DLP API, and move the data to either the Sensitive or Non-Sensitive bucket.
60%Community converges on D. Official key confirms.
10 votes · last validated recently
// explanation
Incoming files should land in a Quarantine bucket so unclassified data is never exposed in production storage. The DLP API scans quarantined objects and routes them to Sensitive or Non-sensitive buckets only after PII classification, preventing unauthorized access to raw PII.
contributed by
N1
@netdiver· revised by @cloud_chris// coverage · 6 domains
What this bank tests.
D113%
Architecting low-code ML solutions53 q
D214%
Collaborating within and across teams to manage data and models37 q
D318%
Scaling prototypes into ML models107 q
D420%
Serving and scaling models58 q
D521%
Automating and orchestrating ML pipelines49 q
D614%
Monitoring ML solutions35 q
// composition
By format & difficulty.
// by format
99%
single · 334multi · 5
// by difficulty
easy
84· 25%
medium
235· 69%
hard
20· 6%
// contributors · 0 engineers
Built by people who took the exam.
Every question is contributed by someone who recently sat Professional Machine Learning Engineer, then reviewed by an SME before landing in the bank. These are the most prolific contributors.
No contributors for this exam yet. Be the first to contribute a question.
// community questions
Questions from the community
Top-voted approved contributions for this exam, reviewed before landing in the bank.
// top community questionsview all →
// compare
One bank, or the whole platform?
this bank
$10.00· one-time
platform · subscribed
$10.00· per month
This bank
All other banks · 23+ exams
Lifetime access
All future updates included
Personal analytics + retention
Cancel anytime
—
// 0 reviews
0.0/ 5
5
0
4
0
3
0
2
0
1
0
No reviews yet. Be the first to share your experience with this question bank.
// faq
Things buyers ask before they buy.
Q.
Can I practice for free?
Free practice questions are available without payment; anyone can start practicing at no cost.
Q.
What do subscribers get?
Subscribers unlock the full practice question bank for each certification exam.
Q.
How much can I see without a subscription?
Approximately 1/2 of the question bank is accessible without a subscription.
Q.
What is the passing score?
The official passing mark for this exam is Pass/fail (Google Cloud does not publish a numeric cut score).
Q.
How long is the certification valid?
The certification is valid for 2 years. Recertify before expiry by passing the current standard exam, a shorter renewal exam where offered, or completing designated Google Skills courses or skill badges.
Q.
What experience is recommended?
3+ years of industry experience including 1+ years designing and managing ML solutions using Google Cloud (per Google Cloud exam page).
// related
You may also like
Discover more exams based on your interests.
// ready when you are
339 questions. 92% pass rate. $10.00 once.
Lifetime access · all updates included · 30-day refund