Etsy Interview Questions & Experiences

Etsy·Data Scientist·Onsite - System Design / Architecture

Jul 2026

Etsy data scientist interview that was basically one very long system design question about search autocomplete ranking. The scope was massive and I kept second-guessing how deep to go on each part.

Given query and click log data with fields like user ID, timestamp, locale, device, typed prefix, suggested term, position, click indicator, dwell time, downstream query, and eventual success, design an ML system to re-rank autocomplete candidate suggestions for each prefix.
What labels best capture long-term user success in an autocomplete system, and how do you construct train/validation splits that avoid temporal leakage?
How would you correct for position and selection bias in the click logs, for example through counterfactual logging, inverse propensity weighting, or randomized interleaving?
What feature sets would you use, covering contextual signals, lexical features, popularity time series, and semantic embeddings, and how do you handle multilingual text and Unicode normalization?
What model architecture would you choose given latency and memory constraints at serving time, and what's your fallback strategy for cold-start terms or new users?
How would you limit feedback loops, concept drift, and surfacing of unsafe or low-quality suggestions over time?
Walk through your offline and online evaluation plan for this system, including what rollback criteria you would set.

“This was a lot.”

View Post

Etsy·Data Scientist·Technical Phone Screen

Jul 2026

Etsy data scientist interview with a live coding block plus some surprisingly involved planning questions. The intern-level framing threw me a bit since the questions felt more structured than I expected for a summer role.

During a 20-minute live coding session with Q&A, how do you structure your communication so the interviewer can follow your thinking in real time? Walk through your approach from clarifying requirements to optimizing your solution.
As a summer intern with a manager who operates in an advisory capacity and weekly group check-ins, lay out a four-week project plan covering goals, demo schedule, risk tracking, how you'd handle the project expanding to a team, and how you'd ask for feedback or work through disagreements.

“I've fumbled this before by jumping straight into code and then having to backtrack mid-session, which looks worse than just pausing upfront.”

View Post

Etsy·Data Scientist·Onsite - System Design / Architecture

Jul 2026

System design round at Etsy for a Data Scientist role, focused entirely on building an autocomplete service from scratch. Pretty deep dive, lots of follow-ups on tradeoffs I wasn't fully prepared for.

Design an autocomplete service that handles up to 5 million UTF-8 words with popularity scores, returns the top 5 prefix-matched suggestions after each keystroke, supports ~1,000 inserts/deletes per second, and meets sub-20ms p99 latency at 5,000 QPS within 300MB of memory.
Which data structure would you choose for this autocomplete system and why, comparing options like compressed tries, ternary search trees, DAWGs, or sorted arrays with binary search?
How would you maintain a top-5 list per prefix without blowing up memory, for example using small heaps, shared postings lists, or lazy enumeration?
How do you handle dynamic updates (inserts and deletes at ~1,000 per second) while supporting concurrent reads with correctness guarantees?
If fewer than 5 exact prefix matches exist, how would you backfill suggestions using edit-distance-1 candidates efficiently?
How would you paginate results beyond the top 5 while keeping the ordering stable across requests?
What are the edge cases you'd want to stress-test, and how would you handle things like very long shared prefixes, non-ASCII input, or an empty prefix query?

“This was the main question and it ate the whole session.”

View Post

Etsy·Data Scientist·Technical Phone Screen

May 2026

Etsy data scientist interview with a meaty product analytics case about listing quality. The whole thing was one big open-ended scenario and they clearly wanted to see if you could connect metrics to actual business outcomes rather than just rattle off a list of numbers.

You're a product analyst at an online marketplace. How would you define and measure listing quality, and how would you set up a system to continuously monitor and improve it over time?

“This question is deceptively wide.”

View Post

Etsy·Software Engineer·Technical Phone Screen

May 2026

Etsy Applied Scientist interview that was basically a live debugging session on a broken NLP training pipeline, with some ML fundamentals thrown in when you least expected them. The code had like seven bugs stacked on top of each other and the clock was not your friend.

A dataset class is returning labels as raw strings instead of tensors. How do you find and fix this in a training pipeline?
There's a one-hot encoding helper function with a dimension mismatch bug. Walk through how you'd diagnose and fix it.
A custom BERT-based model has dropout placed incorrectly and some BERT layers have wrong requires_grad settings. What problems does this cause and how do you fix it?
The model is using last_hidden_state incorrectly, either pulling the wrong token or averaging over padding tokens. How do you identify and fix this?
Softmax is being applied to the model output before CrossEntropyLoss. Why is this a bug and what do you do about it?
The AUC metric is being called with incorrect arguments, passing logits instead of probabilities and using the wrong multi-class configuration. How do you fix this?
Interspersed ML fundamentals: things like why does dropout help generalization, what does the CLS token represent, when would you freeze pretrained weights vs fine-tune everything.

“This one I spotted fast, which gave me false confidence.”

View Post