NewFree internships, no fees

AI and data

Machine Learning Engineer job simulation

Join a data science team as a junior ML engineer: train and document a cancellation model, catch target leakage, choose the threshold with costs, and handle a fairness gap and drift after release.

Machine Learning Engineer job simulation
  • Free: days 1 to 5, about 10 h 30 min of tickets
  • Premium: days 1 to 20
  • Checked as you go
  • Reviewed 19 Oct 2026

The project

You join Tarn Valley Data Science Ltd (simulated company)

Tarn Valley Data Science Ltd (simulated company) is a applied machine learning consultancy in Leeds. You help its team deliver a project for Pennine Fitness Clubs Ltd (simulated company), at Member retention model for twelve clubs (ticket MLE-088).

You are the junior ML engineer on a member-cancellation model for a chain of fitness clubs. The Senior ML Engineer gives you a ticket, a training extract with planted problems, a plan with mistakes in it and a log of experiments, one of which scored 0.99. Over four weeks you count what is really in the data, prove where the too-good score came from, find that 97 percent accuracy is the baseline, choose a threshold with costs and a call capacity, handle a change request, and then deal with the model after release: a fairness gap, a changed door system, drift and a deletion request.

The people in the story are roles, such as Lead Engineer, not real people.

What you will do

By the end you will have

  • Profile a dataset for a datasheet and review a training plan for leakage, splits and the wrong metric
  • Prove where a too-good AUC comes from and explain why 97 percent accuracy on 3 percent positives means nothing
  • Choose a threshold with a cost matrix and the capacity of the people who act on the list
  • Check a model by age band, write the model card honestly and refuse to hide a gap
  • Read monitoring after release, find the upstream change that caused drift, and hand over with numeric retrain triggers

Day by day

The plan, ticket by ticket

Self-paced. A day opens when you hand in the previous day's tickets.
Machine Learning Engineer job simulation plan
DayTicketKindTimeEdition
1Induction: team standards for machine learningQuiz40 minFree
1Datasheet: count what is really in members.csvTable1 h 10 minFree
2Review the feature spec and training planDocument review1 h 20 minFree
2Lab: data health check on the customer table3D lab1 hFree
3EXP-015: prove where the 0.99 comes fromCalculation1 h 10 minFree
3Lab: train and evaluate without leakage3D lab1 h 10 minFree
4What does 97 % accuracy mean on 3 % positives?Calculation1 h 15 minFree
4"97 % is excellent. Switch it on tomorrow, and use deep learning."Decision35 minFree
5Lab: choose the metric and the threshold3D lab1 h 10 minFree
5EXP-017 record and end-of-week statusWriting1 hFree
6Choose the threshold with the cost matrix and the call capacityTable1 h 40 minPremium
7Review the draft model card v1.2Document review1 h 30 minPremium
8Impact note for change request CR-02Writing1 h 50 minPremium
9Lab: overfitting, tune the tree3D lab1 h 20 minPremium
10Experiment log: gaps and candidatesTable1 h 10 minPremium
11Measure the door system change in the training fileCalculation1 h 10 minPremium
12Drift after release: list size, recall, precisionCalculation1 h 30 minPremium
13Lab: fairness check3D lab1 h 20 minPremium
14Results by age band on our own modelCalculation1 h 20 minPremium
15"Leave the age slice out of the board report"Decision40 minPremium
16Risk note: Map, Measure, Manage, GovernWriting1 h 20 minPremium
16A member asks us to delete her dataDecision40 minPremium
17Review pull request 31: the v1.2 training pipelineDocument review1 h 30 minPremium
18Capstone: the release pack for the member cancellation modelHand-in4 hPremium
19Handover note to the platform teamWriting1 h 10 minPremium
20A conversation about your own workViva50 minPremium

Real documents

The documents you will work with

Project documents
NumberDocumentRevEdition
MLE-TKT-088Ticket MLE-088: churn model v1 for the retention teamAFree
MLE-STD-001Data science team standards (one page)CFree
MLE-FRM-001Problem framing: member cancellation within 30 daysAFree
MLE-DSH-001Datasheet for the member snapshot dataset0.2Free
MLE-FSP-001Feature specification and training plan v0.4AFree
MLE-EXP-001Experiment logCFree
MLE-MCD-001Model card v1.2: member cancellation model (EXP-017)APremium
MLE-CHG-002Change request CR-02: predict cancellation within 60 days and add the Family planAPremium
MLE-FRM-001Problem framing: member cancellation within 60 days (model v2)BPremium
MLE-PCN-014Platform change notice PCN-14: door system upgradeAPremium
MLE-MON-001Monitoring plan and weekly monitoring fileAPremium
MLE-PRQ-031Pull request 31: training pipeline for model v1.2APremium
MLE-HOV-001Release and handover pack requirementsAPremium
MLE-EXP-001Experiment log, with the tree-depth runsDPremium

Tools

In the industry, and here

In the industryHere
Python with scikit-learn and a notebookYour own notebook or spreadsheet on the downloaded files; every answer can be found with either
Experiment tracking (run ids, parameters, metrics)A numbered experiment log document and the experiment record you write
Model cards, datasheets and a risk registerReviewed documents with numbers and revisions
Monitoring dashboard and ticket trackerA weekly monitoring file and numbered tickets in the inbox

Standards

The standards the work follows

  • CRISP-DM
  • Model Cards for Model Reporting
  • NIST AI RMF 1.0

Prepare

Labs and study materials

Free, and linked where a ticket needs them.

3D labs used

Study before you start

What you get

Free, certificate and Premium

Free

Days 1 to 5, every ticket checked, model answers, the 3D lab and a profile entry.

Free

Certificate (optional)

  • A graded, verifiable certificate with your score and band
  • A public verification page and QR code
  • One-click add to LinkedIn as a licence or certification
  • A Verified mark on your profile entry

₹499

Premium

Premium job simulation

  • The full four-week project: change requests, site work, faults and handover
  • A capstone deliverable reviewed by an engineer
  • An AI viva on your own work
  • The graded certificate and a work record PDF with your skill scores
  • Priority help from our team
₹1,499The certificate is included. If you bought it, its price is credited.

On your profile

How it shows on your profile

It shows on your EDWartens profile under Work experience, marked as a job simulation.

Work experience

Machine Learning Engineer (job simulation)

Tarn Valley Data Science Ltd (simulated company)

10 h 30 min active hours logged · Your dates

Verified, with the certificate

A job simulation is a realistic training project at a simulated company. It is not employment, an internship or a work placement. Hours are active hours the learner logged on EDWartens.

Questions

Quick answers

Do I need to code?

No. The tasks are checked as numbers, decisions and writing, and the labs run in the browser. Python helps with the CSV files, but a spreadsheet works for every calculation.

Is this a real company and a real model?

No. Tarn Valley Data Science and Pennine Fitness Clubs are made-up, the data is synthetic and generated with planted problems. The documents, tickets and situations follow what a junior ML engineer meets on a real project.

How long does it take?

The free week is about ten hours of work spread over five days. The full Premium edition runs over twenty working days and roughly thirty to forty hours, at your own pace.

Which libraries or cloud do I have to use?

None. The content is vendor-neutral. The answers are checked as numbers, so any tool that can count and rank works.

What do I get at the end?

A work record with your scores by task and skill, which shows on your EDWartens profile under Work experience, marked as a job simulation.

Is the Machine Learning Engineer job simulation free?

Yes, to start. Days 1 to 5 are free. The certificate and the Premium edition are optional and are priced on this page in your currency.

Does it count as work experience?

It shows on your EDWartens profile under Work experience, marked as a job simulation. It is not employment. A job simulation is a realistic training project at a simulated company. It is not employment, an internship or a work placement. Hours are active hours the learner logged on EDWartens.

Keep going

Jobs and internships like this

Last reviewed 19 October 2026.