Swiggy
Leading Indian food delivery aggregator with complex real-time logistics.
4 Rounds
~15 Days
Hard
The Interview Loop
Recruiter Screen (30 min)
Standard fit check, behavioral questions, and resume overview.
Technical Loop (3-4 Rounds)
Deep dive into domain knowledge, coding, and system design.
Interview Question Bank
Data Scientist
•
Behavioral
•
medium
Tell me about a time you had to push back on a product manager's request because the data didn't support it.
#Communication
#Stakeholder Management
#Data-Driven Decision Making
Data Scientist
•
Behavioral
•
medium
Describe a situation where your deployed ML model's performance degraded over time. How did you detect and fix it?
#MLOps
#Model Drift
#Monitoring
#Problem Solving
Data Scientist
•
Behavioral
•
easy
Tell me about a time you had to explain a complex machine learning concept to a non-technical stakeholder.
#Communication
#Storytelling
#Business Acumen
Data Scientist
•
Behavioral
•
medium
Describe a time you took the initiative to optimize an existing process or model without being asked.
#Proactivity
#Impact
#Continuous Improvement
Data Scientist
•
Behavioral
•
medium
Tell me about a time you had to work with a highly imbalanced dataset. What techniques did you use and why?
#Imbalanced Data
#SMOTE
#Class Weights
#Evaluation Metrics
Data Scientist
•
Coding
•
medium
Write a SQL query to find the top 3 restaurants in each city based on the number of completed orders in the last 30 days.
#Window Functions
#Aggregations
#Date Functions
Data Scientist
•
Coding
•
hard
Given a dataset of delivery coordinates, write an algorithm to find the optimal route for a delivery executive carrying batched orders.
#Graph Theory
#Traveling Salesperson Problem
#Heuristics
#Dynamic Programming
Data Scientist
•
Coding
•
easy
Write a Python function to calculate the Haversine distance between two GPS coordinates (restaurant and customer).
#Math
#Geospatial
#Python
Data Scientist
•
Coding
•
hard
Write a SQL query to calculate the week-over-week retention rate of new users who joined in Q1.
#Cohort Analysis
#Self Joins
#Date Manipulation
Data Scientist
•
Coding
•
medium
Given an array of integers representing order delivery times, write a function to find the longest contiguous subarray with an average delivery time below a given threshold.
#Sliding Window
#Arrays
#Prefix Sum
Data Scientist
•
Coding
•
medium
Write a SQL query to find delivery executives who have a cancellation rate of more than 5% but have completed at least 100 orders.
#Filtering
#Aggregations
#Having Clause
Data Scientist
•
Coding
•
easy
Write a Python script to parse a large JSON log file of user clicks and return the top 5 most frequently clicked restaurant IDs.
#Data Parsing
#Hash Maps
#Heaps
#Python
Data Scientist
•
Coding
•
hard
Write a SQL query to calculate the median order value for each user segment (e.g., Swiggy One vs. Non-Swiggy One).
#Percentiles
#Window Functions
#Advanced SQL
Data Scientist
•
Coding
•
medium
Write a Python function to find the maximum overlapping active orders given a list of order start and end times.
#Sorting
#Intervals
#Sweep Line Algorithm
Data Scientist
•
System Design
•
hard
Design an ETA (Estimated Time of Arrival) prediction system for Swiggy food delivery.
#Machine Learning Architecture
#Real-time Systems
#Regression
#Feature Engineering
Data Scientist
•
System Design
•
hard
How would you design a dynamic surge pricing model during peak hours or bad weather?
#Dynamic Pricing
#Supply and Demand
#Optimization
#Reinforcement Learning
Data Scientist
•
System Design
•
medium
Explain how you would build a recommendation engine for Swiggy Instamart to cross-sell items during checkout.
#Recommender Systems
#Collaborative Filtering
#Market Basket Analysis
#Deep Learning
Data Scientist
•
System Design
•
medium
Design a machine learning model to detect promo code abuse by users creating multiple accounts.
#Fraud Detection
#Anomaly Detection
#Graph Neural Networks
#Classification
Data Scientist
•
System Design
•
hard
How would you build a search ranking algorithm for restaurants when a user searches for a generic term like 'Biryani'?
#Information Retrieval
#Learning to Rank
#Personalization
#NLP
Data Scientist
•
System Design
•
medium
Design a system to automatically classify customer support chat tickets into categories (e.g., refund, delayed order, missing item).
#Text Classification
#NLP
#LLMs
#System Architecture
Data Scientist
•
System Design
•
hard
Design a system to predict whether an ongoing order will be delayed, so proactive communication can be sent to the customer.
#Streaming Data
#Event-driven Architecture
#Classification
#Kafka
Data Scientist
•
System Design
•
medium
Design an ML pipeline to identify and remove duplicate restaurant listings created by partners trying to game the system.
#Entity Resolution
#Fuzzy Matching
#Embeddings
#Clustering
Data Scientist
•
System Design
•
hard
Design a system to suggest autocomplete queries as a user types in the Swiggy search bar, considering their past order history.
#Trie Data Structure
#Caching
#Personalization
#Low Latency
Data Scientist
•
Technical
•
hard
How do you handle network effects and interference when running an A/B test on a new delivery batching algorithm?
#A/B Testing
#Experimentation
#Network Effects
#Causal Inference
Data Scientist
•
Technical
•
medium
Explain the mathematical difference between XGBoost and Random Forest. Why might one perform better for ETA prediction?
#Ensemble Methods
#Gradient Boosting
#Decision Trees
#Bias-Variance Tradeoff
Data Scientist
•
Technical
•
hard
How would you forecast the daily inventory requirement for perishable goods in a Swiggy Instamart dark store?
#Time Series Forecasting
#ARIMA
#Prophet
#Deep Learning
Data Scientist
•
Technical
•
medium
Explain how you would use NLP to extract and categorize menu items from raw text or images of physical menus.
#NLP
#OCR
#Named Entity Recognition
#Transformers
Data Scientist
•
Technical
•
medium
What metrics would you track to evaluate the success of a new personalized homepage feed on the Swiggy app?
#Product Metrics
#A/B Testing
#User Engagement
Data Scientist
•
Technical
•
medium
How would you handle missing or noisy GPS pings from delivery executives' phones when calculating historical travel times?
#Data Cleaning
#Imputation
#Geospatial Analysis
#Kalman Filters
Data Scientist
•
Technical
•
medium
How do you address the cold start problem for a newly onboarded restaurant in our recommendation system?
#Recommender Systems
#Cold Start
#Content-based Filtering
#Heuristics
Data Scientist
•
Technical
•
hard
Explain the concept of Multi-Armed Bandits. How could Swiggy use this for optimizing banner ads on the app homepage?
#Reinforcement Learning
#Multi-Armed Bandits
#Exploration vs Exploitation
Data Scientist
•
Technical
•
medium
How would you model the probability of a delivery partner accepting an order assignment?
#Classification
#Logistic Regression
#Feature Engineering
#Behavioral Modeling
Data Scientist
•
Technical
•
hard
How would you evaluate the trade-off between delivery speed and batching efficiency (combining multiple orders)?
#Optimization
#Trade-off Analysis
#Simulation
#Business Metrics
Data Scientist
•
Technical
•
medium
What loss function would you use for a model predicting the exact preparation time of food at a restaurant, and why?
#Loss Functions
#Regression
#Asymmetric Loss
Data Scientist
•
Technical
•
hard
How would you use causal inference to determine if a recent discount campaign actually drove incremental orders or just subsidized existing demand?
#Causal Inference
#Difference-in-Differences
#Propensity Score Matching
#Incrementality
Difficulty Radar
Based on recent AI-sourced data.
Meet Your Interviewers
The "Standard" Interviewer
Senior EngineerFocuses on core competencies, system constraints, and clear communication.
SimulateUnwritten Rules
Think Out Loud
Always explain your thought process before writing code or drawing architecture.