Swiggy

Swiggy

Leading Indian food delivery aggregator with complex real-time logistics.

4 Rounds ~15 Days Hard
Start Mock Interview

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 work with a highly imbalanced dataset. What techniques did you use and why?

#Imbalanced Data #SMOTE #Class Weights #Evaluation Metrics
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 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

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 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 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 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 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 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
Machine Learning Engineer Technical easy

In our fraud detection dataset, only 0.1% of transactions are fraudulent. How do you train a robust model on this highly imbalanced data?

#Classification #Imbalanced Data #Loss Functions
Machine Learning Engineer Technical medium

If an offline recommendation model shows a 10% improvement in NDCG, but the online A/B test shows a drop in conversion rate, what could be the reasons?

#A/B Testing #Evaluation Metrics #Offline-Online Discrepancy
Machine Learning Engineer Technical medium

What is the difference between AUC-ROC and PR-AUC? Why is PR-AUC generally preferred for evaluating models on highly skewed datasets?

#Evaluation Metrics #Probability #Imbalanced Data
Machine Learning Engineer Technical medium

Explain Matrix Factorization in the context of collaborative filtering. What are its main limitations when applied to a fast-changing catalog like Swiggy Instamart?

#Recommender Systems #Linear Algebra #ALS #Collaborative Filtering
Machine Learning Engineer Technical medium

Explain the difference between pointwise, pairwise, and listwise learning to rank. Which approach would you use for Swiggy's dish search, and why?

#Learning to Rank #Information Retrieval #NLP
Machine Learning Engineer Technical medium

How do you handle the cold start problem for a newly onboarded restaurant on Swiggy that has no historical order data?

#Recommender Systems #Cold Start #Content-based Filtering #Heuristics
Machine Learning Engineer Technical easy

What is the difference between NDCG and MAP? In what scenario would you prefer one over the other for evaluating search results?

#Evaluation Metrics #Recommender Systems #Search
Machine Learning Engineer Technical medium

Why is XGBoost often preferred over Random Forest for tabular data tasks like ETA prediction? Explain the mathematical difference in how they build trees.

#Tree Models #Ensemble Methods #Gradient Boosting

Difficulty Radar

Based on recent AI-sourced data.

Meet Your Interviewers

The "Standard" Interviewer

Senior Engineer

Focuses on core competencies, system constraints, and clear communication.

Simulate

Unwritten Rules

Think Out Loud

Always explain your thought process before writing code or drawing architecture.

Practice Now