DoorDash Machine Learning Engineer interview questions

21 Machine Learning Engineers have shared notes from their DoorDash interviews, with the questions they were asked in each round. That is 13% of the 160 DoorDash interview notes on Screna AI.

21 Machine Learning Engineer interview notes

DoorDash·Machine Learning Engineer·Technical Phone Screen

Jun 2026
DoorDash ML engineer round, one coding question framed around their delivery business. Pretty much a scheduling problem dressed up in rider/order language.
  • Given a list of delivery orders where each order has a start time and end time representing when a rider is occupied, find the minimum number of riders needed to handle all orders simultaneously.

“Classic interval overlap problem, just reworded.”

View Post

DoorDash·Machine Learning Engineer·Technical Phone Screen

Jun 2026
DoorDash MLE interview with a meaty system/product debugging question about order fulfillment. Not a coding round, more of a structured thinking exercise where they want you to cover a lot of ground without losing the thread.
  • A customer receives items that don't match what they ordered. Walk through every possible cause across the full order pipeline, from the customer placing the order to the courier dropping it off, and explain how you'd prioritize investigating each category.

“This one sprawls fast if you're not careful.”

View Post

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

Jun 2026
DoorDash MLE system design round focused entirely on ads infrastructure. No ML theory, just backend: how you store, retrieve, rank, and pace ads at scale. Harder than I expected to keep the scope tight.
  • Design an ads recommendation and serving system, focusing on the backend infrastructure rather than the ML model itself.
  • How would you handle budget pacing for advertisers to prevent overspending or underspending within a campaign window?
  • How would you design the click and impression tracking pipeline to ensure exactly-once billing?
  • Walk through how you would retrieve candidate ads for a given user and context at low latency and high throughput.
  • What are the non-functional requirements you would prioritize for an ads serving system, and how do they create tensions with each other?

“This is a beast of a question because it sounds like an ML design problem but they explicitly want you off the model and onto the plumbing.”

View Post

DoorDash·Machine Learning Engineer·Technical Phone Screen

Jun 2026
DoorDash ML Engineer interview where the whole thing basically revolves around one project deep-dive. They will keep pulling threads until they find something you can't explain, so you better actually know your own work cold.
  • Walk me through a project you've worked on, including your specific contributions, the technical decisions you made, what alternatives you considered, how you collaborated with others, what went wrong, and what the measurable outcomes were.

“This is not a 'tell me about a project' question.”

View Post

DoorDash·Machine Learning Engineer·Technical Phone Screen

Jun 2026
DoorDash MLE interview was a single open-ended ML case study, basically one long conversation covering everything from how you'd frame a problem to how you'd monitor it in production. No coding, just a lot of 'and then what?' follow-ups.
  • Pick a DoorDash ML problem (like ETA prediction or dasher dispatch) and walk me through how you'd frame it, including what metrics you'd care about.
  • What data sources and features would you use for the problem you chose?
  • Walk through your candidate models, from a simple baseline up to something more complex. What would you actually start with and why?
  • How would you set up training and evaluation for this system? What pitfalls would you watch out for?
  • What are the deployment constraints you'd care about, specifically around latency and feature freshness?
  • How would you design an A/B test to measure whether your new model is actually better?
  • Once the model is live, how do you monitor it and what failure modes would you plan for?

“I went with ETA prediction because it felt concrete.”

View Post

DoorDash·Machine Learning Engineer·Technical Phone Screen

Jun 2026
DoorDash ML engineer screen, one coding problem the whole time. Pretty applied, not your typical leetcode grind, which I wasn't expecting.
  • Given an n x n grid and a list of restaurants, each defined by a position, a delivery radius, and a delivery count, compute a heatmap where each cell holds the total expected number of deliveries from all restaurants that cover it.

“The base version isn't too bad once you think of it as just iterating over each restaurant's bounding square and adding d to every cell inside it.”

View Post

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

Jun 2026
DoorDash ML system design round focused entirely on infrastructure, not modeling. The scope was wide enough that I kept second-guessing whether I was going too deep on one area and neglecting others.
  • Design the end-to-end ML infrastructure for a large-scale product, covering the full training and inference pipeline at a high level.
  • How would you design a feature store that supports both online low-latency lookups and offline batch training?
  • Walk through how you'd handle experiment management, including A/B tests, shadow deployments, canary rollouts, and rollbacks.
  • How would you ensure reproducibility across training runs?
  • How would you design the serving stack to meet sub-100ms online inference latency at scale, and what tradeoffs exist between CPU and GPU serving?
  • What's your approach to monitoring for data drift, model drift, and training/serving skew in production?
  • How would you handle multi-tenant isolation and cost optimization in a shared ML infrastructure?

“I started with data ingestion and worked forward, which felt logical but probably wasted time on stuff they didn't care about.”

View Post

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

Jun 2026
DoorDash ML engineer system design round focused entirely on building a restaurant recommendation system. The emphasis was less on model internals and more on the infrastructure side, which I wasn't fully expecting.
  • Design a restaurant recommendation system, focusing on the deployment and serving infrastructure rather than model internals.
  • What are the functional and non-functional requirements for a restaurant recommendation system, including latency targets, data freshness, and scale?
  • How would you distinguish between long-term static features and short-term real-time features in this system, and where would you store each?
  • How do you ensure consistency between online serving and offline training in an ML system like this?
  • How would you set up logging, monitoring, and A/B testing for this recommendation system?
  • How would you handle cold start for new users and new restaurants, and what fallback strategies would you use?

“I spent the first few minutes going too deep into model architecture and they redirected me pretty quickly.”

View Post

DoorDash·Machine Learning Engineer·Onsite - Behavioral / Leadership

Jun 2026
DoorDash ML engineer interview that leaned hard into the resume deep-dive format. One project, lots of follow-ups, and they really wanted to know what the numbers looked like after launch.
  • Pick a project from your resume and walk me through it end-to-end, including what you'd do differently and what business metrics it moved after launch.

“This sounds like a standard resume question until the follow-ups start piling on.”

View Post

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

May 2026
DoorDash ML/product case round, open-ended and pretty broad. The whole thing was one big system design question dressed up as a business case, which I wasn't fully expecting.
  • Design a system to send promotional offers like discounts and coupons to drive consumer growth. Walk through your goals and metrics, how you'd pick the target audience, how you'd assign treatments using uplift modeling, how you'd handle budget constraints, how you'd run A/B tests, and how you'd distinguish long-term retention from short-term redemption effects.

“This one sprawled in a way that made it hard to stay organized.”

View Post