DoorDash

Pro

ML Engineer interview prep

Based on 6 reports for mid-level candidates, the Machine Learning Engineer interview loop at DoorDash is heavily SWE-inclusive (coding/system-design heavy) and focuses on engineering fundamentals. Technical assessments typically feature medium to hard algorithmic problems involving graph traversal, interval manipulation, and the implementation of data structures. The process also evaluates domain knowledge, behavioral fit, and ML-specific coding, though general software engineering skills carry the most weight.

Based on 6 interview reports · 116 questions

L4L5 · SeniorL6 · Staff

System Design12

·Design DoorDash's homepage ranking system. Millions of users open the app expecting personalized restaurant/grocery/reta
·Design the real-time feature store for DoorDash's homepage ranking. Features include user history (orders, searches, car
·Design DoorDash's cross-category recommendation system. A user who orders Thai food should also see relevant grocery rec

Domain Knowledge96

·Explain multi-task learning architectures for ranking: shared-bottom, MMoE, PLE, and AITM. For each, derive the gradient
·Walk through two-tower retrieval end-to-end. Derive the training objective. What information leakage problems arise when
·Explain position bias in ranking from first principles. Derive the IPW estimator and its variance problem. Compare resul

Behavioral8

·You're the most senior ML engineer on a team of 6. Two mid-level engineers keep proposing overly complex model architect
·You've been asked to lead the technical strategy discussion for your team's next-year ML roadmap. Product wants 5 new fe
·You need to convince a product manager and a VP that an ML system is NOT worth building — a simpler heuristic would achi

Ready to prep for DoorDash?

Start your loop