Design a harmful content detection systemML designDetect harmful posts (hate, violence, self-harm, spam) across text and images, with high recall on severe harms and a path to human review.
Last asked Aug 2026
Meta ML design interview
Round 6 of 7 · 11 questions reported
- Format
- ML system design
- Heads-up
- MLE and research tracks replace one or both coding rounds with ML system design and a project deep dive.
Questions Meta asks in this round 11
- Design a large-scale recommendation system end to endML designDesign a recommendation system from scratch. When a user opens a surface, it picks a short, ordered list of items out of a very large catalog that changes all the time, and it…Last asked Jul 2026
- Design a nearby places recommendation systemML designDesign the ML system that recommends places to visit (restaurants, shops, attractions) to a user in a maps or local-discovery product. The user may be on the move, so location and…Last asked Mar 2026
- ML fundamentals deep dive for ML rolesML designAfter a short walk through your resume, expect fast questions on machine learning basics, usually centred on your own area (language models, vision, recommendations). For each…Last asked Jun 2026
- Design an image copyright-violation detection systemML designDesign a system that detects when users upload images that infringe someone's copyright on a large social platform. Discuss where the reference set of protected images comes from…Last asked Feb 2026
- Design a notification ranking systemML designMany products send notifications to the same user: new products, friends' activity, results of advertisers' campaigns and more. Design the ML system that decides which…Last asked Jan 2026
- Design an ads ranking system with calibrated predictionsML designDesign the system that ranks ads for a user, using predicted click and conversion probabilities together with advertiser bids. Because the predictions feed an auction, they must…Last asked Jan 2026
- Design comment ranking for a news feedML designDesign the ML system that decides which comments to show, and in what order, under posts in a news feed. Discuss the objective (meaningful conversations, not only likes), the…Last asked Dec 2025
- Design a large-scale MoE pretraining pipelineML designDesign the training setup for pretraining a mixture-of-experts language model across many GPUs. Cover how experts and other layers are parallelized, token routing and load…Possibly retired
- Design an asynchronous RL post-training systemML designDesign a system for post-training a large language model with reinforcement learning where generation (rollouts) and training run asynchronously. Cover how rollout workers and…Possibly retired
- Design a model that predicts posts a user will dislikeML designDesign a model for a news feed that predicts which posts a user would dislike or hide, so ranking can show fewer of them. Cover the labels (explicit negative feedback is rare)…Possibly retired