Design job click prediction for job ranking
PremiumML systemHard
- Click through rate prediction
- Position bias
- Impression logging
Quick answer
This ML system interview question asks you to design job click prediction for job ranking. Aim for a design that turns data into useful predictions in production, then explain the data, training, serving and monitoring. Interviewers want to see how you frame the problem, measure success and keep the model healthy after launch.
The problem
Design job click prediction for job ranking: a model that predicts whether a member will click a job shown in their job feed or search results, used to rank candidate jobs. The hard parts are honest labels, position bias, impressions that were never seen, time leakage in features, and new postings with no history.
A member opens the jobs tab, retrieval returns 500 candidate jobs, and the ranker must order them in under 80 ms. Postings live about 30 days, and about 1 million new jobs arrive each day with no clicks yet.
What must the system do?
- Click probability: Score each candidate job with a calibrated probability that the member clicks it, and order the list by it.
- New postings: A job posted 5 minutes ago with no clicks must still get a fair score from its content.
How well must it do it?
- Latency: Score 500 candidates in at most 80 ms at p99.
- No leakage: Every training feature is the value the system could have known at the moment of the impression.
What scale should you design for?
Use these numbers in your estimates.
The scale numbers unlock with this questionUnlock
Key concepts
- Click through rate prediction
- Position bias
- Impression logging
- Point in time features
- Cold start embeddings
- Calibration
How you’ll practise
- Problem framing
- Data and labels
- Features and model
- Training and evaluation
- Serving and monitoring
- Wrap-up
Lala, personalized to you, gives a hint when you ask and reviews your design when you are ready.
What do interviewers look for?
In any ML system design round.
- Frames the product goal as a clear ML problem
- Defines offline and online success metrics
- Explains where the data and labels come from
- Separates training from serving and keeps features consistent
- Plans for drift, retraining and rollbacks
- Weighs model quality against latency and cost
Questions people ask about this interview question
- Which design type is this question?
- It is an ML system question. You design job click prediction for job ranking and explain your choices the way you would in an interview.
- Is this question asked at entry level?
- It is marked Hard. It suits engineers preparing for senior interviews, where you are expected to drive the discussion and go deep on trade-offs.
- What should I cover first?
- Start with the product goal, how success is measured and what data is available. Agree on scope with the interviewer before you design anything.
- Can I practise it for free?
- It is a premium question. Sign up and unlock it once for 10 credits; it then stays unlocked. When you finish, Lala, your personalized AI mentor, can review your design for 30 credits.
Related questions
Updated · Written by the SevyDevy team