Interview Questions

Anonymous Wasp - "I was able to provide the optimal approach and coded it up"See full answer

Yair G. - "Are we speaking of all Meta Ads products on something specific? All of them Meta is a social media and AI company that generates most of it's revenue from Ads on social media. Meta's mission is to empower people to build communities and bring the world closer together. If ads violate the community guidelines regulations that can directly hurt both Meta's mission and its revenue stream. For example ads that include hate speech are against community guidelines and also hurts Meta's mission. Ha"See full answer

Kapil D. - "Overall a very good summary of ranking problems. I wish there are more details in the post on depth of modeling. One can talk more about advance ML architectures like DCN, BertRec etc"See full answer

Clayton P. - "I've watched all the ML Systems designs interviews and this solution provides a clean baseline for predicting ETA using historical averages, but it falls short of addressing the broader problem of route planning. The system predicts ETA for a given segment and time interval, but it doesn’t explain how to compute the ETA for an entire route or how to integrate this into dynamic path selection. It also lacks depth on handling real-time data, adapting to distribution shift, or reacting to sudden"See full answer

Manas M. - "Couple of Clarification Questions to be asked are: Aim of the physical product Retention/Encourage Loyalty Attract new customers Collect customer Data outside of the Airbnb ecosystem for better advertising and customer focus User Base of Airbnb Solotravellers - traveling to new places for exploring/solo travel Business Travelers - Lot of business Travelers who own small/medium businesses and book their own travel can choose airbnb Family gr"See full answer

Sdn D. - "Clarifying question: AOV/USER it means that the total price paid by a user in a certain period should be more than what it is now ? Is the average taken on a daily/ weekly/monthly basis ? I would presume it to be a monthly basis , as it helps us a defined period of time to analyse user beharviour and track number of orders. Daily wont be succesfull mertric , as ocassionally only a user may order multiple times in a day , also weekly is also a viable metric but that wont help us to analyse"See full answer

Dinar M. - " Thanks a lot for showing us how a recommender system can be build. I see it was proposed to use Collaborative filtering which is user - item matrix having dimension N * M (where N - number os users and M - number of songs). Though, it was explained how it gonna be built, it is still unclear how all users and songs features are going to be used. In that matrix we have values in cell (lets say i, j) like 1 - a specific user (i) clicked on song (j) when it was recommended or it is 0 when the user"See full answer

Scott S. - "Great question! Before communicating any major change, I would ensure I have a deep understanding of the strategic shift, its rationale, and its implications. This involves meeting with senior management to gather all necessary details and preparing to address any questions or concerns from the team. To share a recent experience I had, so Last year, our senior management decided to shift our focus towards leveraging machine learning and advanced real-time analytics to enhance our trading stra"See full answer

Aekagra S. - "Clarified whether this drop is observed in a particular geography or with a particular demography or devices. Then moved to the analysis of any bugs or flow broken or any defects. If not then talk about any competitor launching a product or feature in a similar category. If yes then double down on that or else speak about any political or marketing campaign that's been launched or any negative news about Facebook. What-Why analysis and concluded with a possible cause."See full answer

Scott S. - "The growth of remote work presented engineering managers with the unique problem of leading scattered teams. Keeping remote workers engaged, motivated, and productive can be a daunting endeavour, but with the appropriate tools and methods in place, it’s possible to bridge the gap caused by physical distance and establish a thriving work environment. One crucial part of managing remote or hybrid teams is good communication. Establishing clear routes of communication and setting expectations fo"See full answer

Anonymous Flamingo - "Design a washing machine for Google Step 1: Building Context through clarifying questions Are we looking at building a complete washing machine(new line of business) or a connected app for washing machine like Android Auto? Any specific geography to look for Goal? Increase usage of any specific google product or introduce smart white goods hardware Step 2: Target users Individuals Single Family Couple Hotels Students Laundromats **Apartments/Studen"See full answer

Apurv W. - "Clarify: Understanding of wallets an UPI What is failure rate here? - transaction failed Is it real time failure or successful on front end but failed in backend - assuming it is front end, real time failure. Have other related products/features experienced the same change? Diagnose (impact, significance) Failure rate = assuming it is significantly increasing Impact = customer lifetime value, # of bookings, Avg order value and satisfaction too. Users & value Seller = Revenue "See full answer

PTL - "Clarify the default pick up location/pin feature - I'm assuming it lets you define a location in settings that is used for pickups unless you over ride it. this is a rider feature. It is not used by the driver to specify where they want to pick up riders Feature goal Make it simpler for the user to book a ride as they no longer need to type in an address when going to the default location User Journey assuming they have already set the default location they open the app cl"See full answer

Tracy C. - "Before I walk you through my thought process, I want to align you with the definition of discovery. I assume discovery is the journey before a guest adds a property or experience to the cart, which can be broken down into the discovery of listings pre-search bar on the homepage and discovery post-search bar on the search results page. Are we talking about both touch points as discovery, or would you like me to focus specifically on one? Is this for a specific platform, mobile or desktop web? Bec"See full answer

Arya R. - "I'm going to assume the problem is limited until the point of where the rider get into the car. Rider segments/characteristics: Local rider (lives and travels in the same city) Tourist rider (visiting a city, using Lyft for the first time in the city) Lets think about some problems for these types of users: Local rider: (Choose to prioritize on these use-cases assuming its a larger % of rides overall) Ride shows as confirmed, but driver does not move on the map Driver does"See full answer