Amazon Interview Questions — Page 81

Amazon·Software Engineer·Technical Phone Screen

May 2026

Amazon SWE interview with a tree problem that looks straightforward until you actually sit down to code it.

Given a binary tree, print the nodes visible from the top view, ordered from left to right.

“I knew what a top view was conceptually but translating that into code took me longer than it should have.”

Amazon·Software Engineer·Technical Phone Screen

May 2026

Brief Amazon interview snippet, just one question about identifying conversations in comment threads. Not much context to go on, but it's the kind of question that sounds deceptively simple until you actually try to define what 'conversation' even means in a comments section.

Given a set of comments, how would you identify which ones form a conversation?

“I'd probably start by thinking about threading: reply chains, timestamps, shared parent IDs.”

View Post

Amazon·Software Engineer·Onsite - Behavioral / Leadership

May 2026

Interviewed for a business analyst role at Amazon and got hit with a behavioral question about data quality and decision-making. Pretty standard stuff for Amazon but it still made me sweat a little.

Tell me about a time you made a decision based on inaccurate or flawed data. What happened and what did you take away from it?

“I had a decent story ready but fumbled the landing.”

View Post

Amazon·Data Scientist·Technical Phone Screen

May 2026

Amazon data scientist interview with a meaty ML question about building a marketing prediction model. One question but it had a lot of moving parts, felt like they wanted to see if you could hold the whole pipeline in your head at once.

You're building a model to predict marketing outcomes. Walk through how you'd use gradient-boosted trees for this, including training, hyperparameter tuning, and evaluation. Also, how do you approach feature selection when you're starting with a large candidate feature set?

“This is deceptively broad.”

View Post

Amazon·Software Engineer·Onsite - System Design / Architecture

May 2026

Amazon system design round for a software engineer role. The problem was building an in-memory pub-sub system from scratch, which sounds manageable until you actually have to think through thread safety and ordering guarantees at the same time.

Design a simplified in-memory publish-subscribe system for a single machine. It should support subscribing to topics with an integer priority, unsubscribing, and publishing messages. Messages must be delivered to subscribers in descending priority order, with earlier subscribers winning ties. The implementation must be thread-safe for concurrent operations.

“I started with the data structures and that was the right call.”

View Post

Amazon·Software Engineer·Onsite - System Design / Architecture

May 2026

System design round at Amazon for a software engineering role. The whole session was basically one giant question about building a real-time top-K item ranking service, and they just kept pulling on every thread until there was nothing left to say.

Design a real-time service that ingests a stream of purchase events and continuously computes the top-K most purchased items across multiple rolling windows simultaneously, such as a short sliding window, a 24-hour window, and per-calendar-day totals.
What data structures would you use to maintain top-K at scale, and how do you handle the aggregation across distributed workers?
How would you handle late-arriving, out-of-order, and duplicate events in your event-time processing pipeline?
How would you manage state across windows, including TTL and eviction policies, to avoid unbounded memory growth?
How do you handle hot keys and partition skew in the ingestion pipeline?
Walk through your serving layer design. How do clients query the current top-K per window, and would you support any kind of push-based streaming to clients?
Where do you land on exactly-once vs. at-least-once semantics for this system, and what are the practical implications of that choice?
How would you tune the system to balance latency against accuracy in the top-K results?

“This was the whole interview, basically.”

View Post

Amazon·Software Engineer·Onsite - System Design / Architecture

May 2026

System design round at Amazon focused entirely on building a recommendation engine at massive scale. The question sprawled across candidate generation, ranking, cold start, fairness, and A/B testing guardrails. A lot of ground to cover in one session.

Design a large-scale product recommendation system covering multiple surfaces like the home feed, product detail pages, cart, and email. Walk through use cases, success metrics, and architecture.
How would you handle cold start for both new users and new items in a recommendation system at this scale?
How would you design the exploration vs. exploitation strategy for recommendations, and what role do bandits play?
How would you design A/B tests for a recommendation system, including what guardrail metrics you'd use?
How do you address bias and fairness concerns in a recommendation model, and what about feedback loops?
What monitoring and rollback strategies would you put in place for a live recommendation system?

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

View Post

Amazon·Software Engineer·Onsite - Behavioral / Leadership

May 2026

Amazon behavioral question about resource constraints. Pretty standard leadership principles territory, nothing too surprising.

Describe a situation where you chose to complete a project with fewer resources rather than accepting more.

“This one is really about frugality and ownership, two things Amazon cares about a lot.”

View Post

Amazon·Software Engineer·Technical Phone Screen

May 2026

Amazon SWE coding round, basically just a tree problem. Nothing too wild but I fumbled the recursion a bit before getting it together.

Given the root of a binary tree and two nodes p and q, find their lowest common ancestor.

“I knew this problem but still took a second to get the recursion right in my head.”

View Post

Amazon·Data Scientist·Technical Phone Screen

May 2026

Brutal technical screen for a DS role at Amazon. One massive multi-part question covering basically every angle of tree-based models you can think of, from hyperparameter tuning to latency budgets to SHAP pitfalls. No outcome info available.

Given a binary classification problem with 1M rows, 200 features, 20% missing values, severe class imbalance (1:50), label noise, and a 20ms inference latency constraint, would you choose a Random Forest or Gradient-Boosted Trees model for production? Justify using bias-variance trade-offs, noise robustness, interaction modeling, and behavior under correlated features, and name the key risks.
What concrete starting hyperparameters and tuning ranges would you use for both Random Forest and Gradient-Boosted Trees in this scenario? Walk through how each parameter affects bias, variance, and inference latency.
How would you encode the categorical features, including high-cardinality ones with over 1,000 unique values, while preventing target leakage and keeping inference within the latency budget?
With a 1:50 class imbalance, how do you handle it across training, metric selection, threshold setting, and probability calibration?
Lay out a full 60-minute experiment plan covering data splits, preprocessing, hyperparameter tuning schedule, and leakage detection guardrails. Include a fallback if training runs over time.
In what scenarios would Random Forest outperform Gradient-Boosted Trees for this dataset, and vice versa? Factor in missing value handling, monotonic constraints, correlated features, and distribution shift.
How would you generate and validate feature importances, run partial dependence and ICE analyses, and apply SHAP, while accounting for pitfalls from correlated features and potential leakage? Also, how do you ensure the model meets the 20ms per-example latency requirement at inference?

“This is the kind of question where you think you know the answer immediately (GBT, obviously) and then spend the next five minutes talking yourself into a corner.”

View Post