Airbnb Machine Learning Engineer interview questions

16 Machine Learning Engineers have shared notes from their Airbnb interviews, with the questions they were asked in each round. That is 21% of the 76 Airbnb interview notes on Screna AI.

16 Machine Learning Engineer interview notes

Airbnb·Machine Learning Engineer·Online Assessment (OA)

Jun 2026
Coding round for an MLE role at Airbnb. You get handed a few files and have to manually implement fit and transform methods, then debug and optimize under separate time blocks. Nothing exotic if you write production ML code regularly.
  • Given a set of provided files (including a run script and evaluation script), manually implement the fit and transform methods of an ML transformer so the pipeline runs correctly, then optimize it within a fixed time limit.

“Two phases: 25 minutes to get it working, 35 minutes to make it faster.”

View Post

Airbnb·Machine Learning Engineer·Onsite - Coding / Algorithms

Jun 2026
Coding round for an MLE role at Airbnb. One algorithmic problem, but the float precision angle made it messier than a standard coin change question.
  • Given a set of coin denominations expressed as floats (e.g. 0.25, 0.5, 1.0), determine whether a target value can be made up exactly, or find the minimum number of coins needed.

“Jumped straight into DP with floats and it blew up in my face.”

View Post

Airbnb·Machine Learning Engineer·Technical Phone Screen

Jun 2026
Airbnb ML engineer interview with a coding problem that's basically coin change dressed up in a travel scenario. Cute theming, but the float arithmetic gotcha is what separates people who've seen this before from people who haven't.
  • You have an X-hour layover in Paris and want to fill it exactly with Airbnb experiences. Given a list of experience durations (in hours, one decimal place), and the ability to book the same experience multiple times, find the minimum number of bookings that sum to exactly X hours. Return -1 if it's impossible.

“So it's unbounded coin change, minimum coins, but with decimal values instead of integers.”

View Post

Airbnb·Machine Learning Engineer·Onsite - System Design / Architecture

Jun 2026
ML system design round at Airbnb for an MLE role. The question was meaty and touched basically every layer of the stack, from label construction to serving to fairness guardrails. Felt like a senior-level bar.
  • Design an ML system to identify high-quality Airbnb listings so they can be surfaced more prominently in search and recommendations, while low-quality ones get flagged or coached.

“This one sprawled fast.”

View Post

Airbnb·Machine Learning Engineer·Technical Phone Screen

May 2026
Airbnb ML engineer coding screen, one problem but it kept growing. Started easy enough and then the follow-ups stacked up fast and I wasn't totally ready for all of them.
  • Parse a URL query string into a dictionary, handling keys with no value, repeated keys, and an optional leading '?' character.
  • Extend your solution to handle percent-encoded characters in keys and values, using a provided unquote() function. How do you make sure encoded delimiters like %26 or %3D don't break your parsing logic?
  • How would you handle malformed query strings? Think about empty keys, trailing ampersands, multiple '=' signs in a single pair, and invalid percent-escape sequences.

“The base case felt manageable.”

View Post

Airbnb·Machine Learning Engineer·Onsite - System Design / Architecture

May 2026
Round 3 of the Airbnb MLE loop was a full ML system design session centered on retrieval and ranking, and it ran long. They clearly care a lot about marketplace ranking depth here, more than any other company I've interviewed with.
  • Design a user embedding and two-stage semantic retrieval and ranking system to surface listings a user is most likely to book, with the goal of maximizing booking conversion.
  • How would you handle position bias in your training data for a ranking model?

“This was the whole round basically.”

View Post

Airbnb·Machine Learning Engineer·Technical Phone Screen

May 2026
Airbnb ML engineer interview with a graph/union-find coding problem that's basically a beefed-up version of a well-known accounts merge problem. Pretty standard algorithmic round but the twist of mixing emails and phone numbers as contact identifiers tripped me up more than I expected.
  • Given a list of accounts where each account has a name and a list of contact identifiers (emails and phone numbers), merge accounts that share any common email or phone number. Return the merged accounts with the union of all contacts, and write your own test cases along with a time/space complexity analysis.

“I recognized the base problem pretty fast but the phone number part threw off my initial approach.”

View Post

Airbnb·Machine Learning Engineer·Onsite - Behavioral / Leadership

Apr 2026
Airbnb's core values round for an ML Engineer role. Three questions, all behavioral in flavor but they really want philosophical coherence across your answers, not just competent storytelling.
  • Why Airbnb? How does the company's mission connect to your own values and past work, and what would you specifically want to build or improve here?
  • What do you think is the biggest problem facing the world right now, and why?
  • What cause do you personally care about, and what concrete actions have you taken to support it, whether time, money, or advocacy?

“This is not a soft opener.”

View Post

Airbnb·Machine Learning Engineer·Technical Phone Screen

Apr 2026
Airbnb ML engineer coding round, one question with a follow-up that honestly felt like two separate interviews crammed into one. The core problem was manageable but the extension caught me a bit flat-footed.
  • Given a string of words and a target width W, implement a function that wraps the text into a bordered box of inner width W. Each line should be padded with spaces and surrounded by pipe characters on both sides. Words should only break at word boundaries, and any short final line gets right-padded with spaces.
  • Follow-up: extend your solution to support a multi-column layout. Given a column count and a column width, distribute the article text across multiple columns displayed side-by-side.

“Spent the first few minutes just staring at the output format and making sure I understood what 'inner width' actually meant.”

View Post

Airbnb·Machine Learning Engineer·Technical Phone Screen

Apr 2026
Coding round at Airbnb for an ML Engineer role. The problem was a bowling score calculator, which sounds straightforward until you actually try to handle the 10th frame edge cases cleanly.
  • Given a sequence of rolls in a 10-frame bowling game, compute the total score following standard bowling rules including strike and spare bonuses and the 10th frame's extra rolls.

“The core logic isn't bad but I kept second-guessing the 10th frame.”

View Post