Mid-level interview questionAsked at Pinterest · interview write-up
Design a ranker for ads launched in the last seven days that handles cold start with safe exploration, then hands off smoothly to the mature model.
Model answer
New ads have no ID history, so predict from what generalizes: creative embeddings, advertiser, category and targeting, with priors from similar ads. Explore with a capped traffic budget and Thompson sampling behind a quality floor.
Hand off by blending both models' scores, shifting weight to the mature model as impressions accumulate. Both must stay calibrated, since the auction uses the score directly. Measure later CTR and the revenue cost of exploring.
Practise the rest
40 ML system design questions, 492 in all, each with a model answer. Free.
More from Pinterest interview questions.
More ML system design interview questions
- You need to copy 500 GB of weights to 1,000 GPU workers over shared 10 Gbps links. What's the lower bound on time, and what would you build?
- Design an LLM coding assistant end to end: data, model and evaluation.
- Design a job scheduler for ML training and batch inference on a shared GPU cluster.
- Training a retrieval model over a catalogue of millions of items, you use sampled softmax. Why does it need a correction, and how do you choose the classification loss?
- Design an inference API that converts PDFs into Markdown using several models in stages.
- How can LLMs be incorporated into recommendation systems, from metadata enrichment and cold start to generative retrieval and semantic reranking?