SPOTLIGHT EPISODE: What happens when a physics PhD and former pro poker player decides to break into big tech? Drew sits down with Shawn Strausser to break down how he went from burnout to hired by Meta as a Senior MLE. You’ll hear the full story, from his initial struggles applying to 500+ jobs with no interviews, to the moment a spam-folder recruiting email from Meta changed everything.Along the way, we pause to reflect on Shawn’s live mock ML system design interview, highlighting key moments, strategies, and insights that helped him land a role as a machine learning engineer. If you’re preparing for system design or ML interviews, this one’s packed with gold.Watch Shawn’s full mock interview here: https://youtu.be/Q-g9nGDBUpY?si=pC896LpbRDRvPLNaBook your own mock interview: https://interviewing.ioConnect with Shawn on LinkedIn: https://www.linkedin.com/in/shawn-strausser-93aa8620b/Sign up to book coaching or to watch more interviews in our showcase: https://www.interviewing.ioSee the interviewer’s feedback and transcript here: https://start.interviewing.io/showcase/KQwiaFnBEwALOr view other Meta interviews: https://interviewing.io/mocks?company=metaDisclaimer: All interviews are shared with explicit permission from the interviewer and the interviewee, and all interviews are anonymous. interviewing.io has the sole right to distribute this content.⸻Timestamps:00:00 Introduction00:24 Interview begins: Shawn’s background and path to Meta19:39 Commentary: prepping to perform in interviews23:39 Interview: mock interview begins26:00 Commentary: feedback on outlining and preparation26:35 Interview: data features and fraud detection32:00 Commentary: fusion and feature discussion32:21 Interview: early vs. late fusion36:00 Commentary: bias and human labeling37:00 Interview: modeling architecture and label bias40:41 Commentary: real-world complexity of label bias43:43 Interview: clarifying questions and best practices48:03 Commentary: content fusion and meme example50:41 Interview: pivotal interview moment52:07 Commentary: rehearsal strategy53:45 Interview: mindset, sleep, and sustainability55:41 Final commentary and outro
REPLAY EPISODE: Our candidate is preparing for an upcoming Meta phone screen and takes on two tree-based problems under timed conditions. The first question involves finding the minimum depth of a binary tree, which the candidate solves confidently with both DFS and BFS approaches. The second, more challenging follow-up asks for the smallest subtree containing all the deepest nodes (a classic lowest common ancestor problem with a twist).Throughout the interview, the candidate demonstrates clear communication, strong algorithmic thinking, and a willingness to iterate and explore edge cases. The conversation includes valuable coaching moments around recursion, time/space trade-offs, and the importance of clarity under pressure.This is a valuable watch if you’re preparing for technical screens at top-tier companies, especially those that emphasize tree-based problems and recursive reasoning.Sign up to book coaching or to watch more interviews in our showcase: https://www.interviewing.ioSee the interviewer’s feedback and transcript here: https://start.interviewing.io/showcase/Ytbd1imDj61qOr view other Meta interviews: https://interviewing.io/mocks?company=metaDisclaimer: All interviews are shared with explicit permission from the interviewer and the interviewee, and all interviews are anonymous. interviewing.io has the sole right to distribute this content.Timestamps:00:00 Intro00:01:34 Problem 1 begins00:14:48 Problem 2 begins00:57:04 Feedback and review
REPLAY EPISODE: Curious how to approach large-scale design interviews? This is the level of depth, structure, and clarity that top companies like Stripe and Meta are actively looking for.In this mock system design interview, a senior engineer is asked to design a photo-sharing app (something like Instagram, but from scratch and at massive scale). What follows is a masterclass in thoughtful architecture: from exploring nuanced functional and nonfunctional requirements to tackling schema design, RESTful APIs, and infrastructure choices under realistic constraints.The candidate works through challenges like privacy controls, feed generation, follow request flows, and media storage for 1 billion daily active users—all while communicating clearly and methodically. You’ll see them navigate trade-offs around consistency vs. availability, break down how to serve images efficiently with CDNs, and set up queues for asynchronous photo processing.Sign up to book coaching or to watch more interviews in our showcase: https://www.interviewing.ioSee the interviewer’s feedback and transcript here: https://start.interviewing.io/showcase/B0pirlqbsofXOr view other FAANG interviews: https://interviewing.io/mocks?company=faangDisclaimer: All interviews are shared with explicit permission from the interviewer and the interviewee, and all interviews are anonymous. interviewing.io has the sole right to distribute this content.Timestamps:00:00 Introduction00:58 Interview Begins02:00 Clarifying assumptions: privacy, authentication, feeds06:45 Discussing follow requests and celebrity suggestions09:00 Metadata and interaction features (likes, comments)12:00 Non-functional requirements and scale (1B DAUs!)15:00 Schema design begins: Users and Follows20:00 Designing the Photo entity (metadata, location, blob storage)27:00 Comment schema + verified users31:00 Designing upload & metadata API endpoints35:45 Designing follow request and response APIs41:00 Designing the user’s feed + pagination44:00 High-level architecture begins: services, DBs, queues48:00 Document store vs. relational DB for photo storage52:00 Serving photos via CDN + Follow service interaction56:00 Final review and detailed feedback from interviewer01:00:00 Encouragement on focusing more on requirements depth
REPLAY EPISODE: In this episode of Whiteboard Confidential, an aspiring ML engineer with no formal industry experience impresses a Meta interviewer by tackling a complex system design question: how would you detect fraudulent or scam content on Facebook?Despite never having held an ML job, the candidate delivers a calm, clear, and deeply thoughtful design that rivals what you’d expect from an IC5–IC6 engineer. From feature pipelines and model architecture to deployment strategy and label bias, this interview is packed with insight. The feedback section is especially valuable, touching on how to ask better clarifying questions, start simpler, and negotiate an offer—even in a tough market.A must-watch for anyone preparing for ML system design interviews at top tech companies.Sign up to book coaching or to watch more interviews in our showcase: https://www.interviewing.ioSee the interviewer’s feedback and transcript here: https://start.interviewing.io/showcase/KQwiaFnBEwALOr view other Meta interviews here: https://interviewing.io/mocks?company=metaDisclaimer: All interviews are shared with explicit permission from the interviewer and the interviewee, and all interviews are anonymous. interviewing.io has the sole right to distribute this content.Timestamps:00:00 Introduction and candidate background00:30 System design prompt: ML model to detect scam content13:00 Architecture walkthrough and feature engineering36:00 Modeling strategy, focal loss, and label bias48:00 Interviewer feedback and praise51:00 Advice on simplifying, asking questions, and tradeoffs1:07:00 Meta-specific offer negotiation tips and job market talk
REPLAY EPISODE: In this episode, we have a real mock interview for a Staff Machine Learning (E6) role at Meta, where the candidate is asked to design the recommendation system behind Instagram Reels. This means choosing which short videos to show to billions of users in real time, based on their behavior and interests.The candidate has a strong grasp of ML fundamentals and proposes modern architecture choices like multitask learning and multi-stage ranking. However, they ultimately do not pass the interview—mainly due to time management and not addressing key practical concerns like feedback loops, feature freshness, and production-readiness. The interviewer offers detailed, actionable feedback that gives you a clear picture of what sets apart a good answer from one that meets the E6 bar.If you’re preparing for ML system design interviews at Meta, Google, or other top-tier tech companies, this interview is full of insights to help you sharpen your strategy, improve your pacing, and avoid common pitfalls. Sign up to book coaching or to watch more interviews in our showcase: https://www.interviewing.io See the interviewer’s feedback and transcript here: https://start.interviewing.io/showcase/Mek40HIliiP0 Or view other Meta interviews: https://interviewing.io/mocks?languag=&company=meta Disclaimer: All interviews are shared with explicit permission from the interviewer and the interviewee, and all interviews are anonymous. interviewing.io has the sole right to distribute this content.⸻Timestamps:00:00 Introduction and interview setup00:53 Problem presented: Instagram Reels recommendation system17:00 Candidate defines ML framing and objective38:00 Discussion of candidate generation and ranking model45:00 Interview ends and candidate self-assessment46:30 Feedback begins: time management, pacing issues50:00 Why this would not pass the E6 bar56:00 What the candidate did well and what was missing1:03:00 Final takeaways from the interviewer