Flipkart
Indian e-commerce giant tackling massive supply chain and scale problems.
4 Rounds
~18 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
Machine Learning Engineer
•
Behavioral
•
medium
Tell me about a time you had to deliver a machine learning model under a very tight deadline. How did you prioritize your tasks?
#Bias for Action
#Prioritization
#Agile
Machine Learning Engineer
•
Behavioral
•
medium
Tell me about a time your machine learning model failed or degraded in production. What was the root cause and how did you fix it?
#Ownership
#Debugging
#Post-mortem
Machine Learning Engineer
•
Behavioral
•
medium
Tell me about a time you had a strong disagreement with a senior engineer or PM regarding the choice of an ML algorithm. How did you resolve it?
#Conflict Resolution
#Communication
#Data-Driven Decisions
Machine Learning Engineer
•
Behavioral
•
easy
Give an example of how you demonstrated Flipkart's 'Customer First' value in your previous role.
#Customer Empathy
#Product Sense
Machine Learning Engineer
•
Behavioral
•
medium
Tell me about a time you identified a bottleneck or process inefficiency in your team and took the initiative to fix it.
#Initiative
#Process Improvement
#Automation
Machine Learning Engineer
•
Coding
•
hard
Given a map of delivery locations represented as a weighted graph, write an algorithm to find the shortest delivery route for an Ekart executive that visits all nodes and returns to the hub.
#Graphs
#Traveling Salesperson
#Dynamic Programming
Machine Learning Engineer
•
Coding
•
medium
Implement an LRU Cache. This is often used to cache product details for fast retrieval during high-traffic events.
#Data Structures
#Hash Map
#Doubly Linked List
Machine Learning Engineer
•
Coding
•
medium
Given an array of strings representing search queries, write a function to group all anagrams together. This helps in query normalization.
#Strings
#Hash Map
#Sorting
Machine Learning Engineer
•
Coding
•
medium
Given a list of delivery time intervals for a specific pin code, merge all overlapping intervals.
#Arrays
#Sorting
Machine Learning Engineer
•
Coding
•
medium
Write a function to find the longest palindromic substring in a given search query string.
#Strings
#Dynamic Programming
#Expand Around Center
Machine Learning Engineer
•
Coding
•
easy
Given an array of integers representing product prices, find the maximum profit you can achieve by buying and selling once.
#Arrays
#Greedy
Machine Learning Engineer
•
Coding
•
medium
Given a dictionary of valid words and a search query string with no spaces, write a function to determine if the string can be segmented into a space-separated sequence of valid words.
#Dynamic Programming
#Strings
#Trie
Machine Learning Engineer
•
Coding
•
easy
Given an array of integers, return the indices of the two numbers such that they add up to a specific target.
#Arrays
#Hash Map
Machine Learning Engineer
•
Coding
•
medium
Given a binary tree representing a hierarchical product category structure, write a function to find the lowest common ancestor of two given category nodes.
#Trees
#Recursion
#Depth-First Search
Machine Learning Engineer
•
System Design
•
hard
Design Flipkart's personalized homepage recommendation system. How would you retrieve and rank products for a user with a rich purchase history versus a completely new user?
#Recommendation Systems
#Two-Tower Models
#Cold Start
#High Throughput
Machine Learning Engineer
•
System Design
•
hard
Design an Estimated Time of Arrival (ETA) prediction system for Flipkart logistics. What features would you use and how would you handle real-time traffic changes?
#Geospatial Data
#Regression
#Real-time Streaming
Machine Learning Engineer
•
System Design
•
hard
Design a dynamic pricing engine for Flipkart. How would you adjust prices in real-time based on inventory, competitor pricing, and demand elasticity?
#Reinforcement Learning
#Time Series
#Optimization
Machine Learning Engineer
•
System Design
•
hard
Design a visual search system (Search by Image) for Flipkart Fashion. How do you generate and index the image embeddings?
#Computer Vision
#Vector Databases
#ANN Search
Machine Learning Engineer
•
System Design
•
medium
Design a system to detect fake reviews on Flipkart product pages. What features and models would you use?
#NLP
#Anomaly Detection
#Graph ML
Machine Learning Engineer
•
System Design
•
medium
Design an auto-complete and spell-correction system for the Flipkart search bar. Latency must be under 50ms.
#Trie
#Caching
#Information Retrieval
Machine Learning Engineer
•
System Design
•
hard
Design an Ad Click-Through Rate (CTR) prediction system for Flipkart's sponsored products. The model needs to update continuously.
#CTR Prediction
#Online Learning
#DeepFM
Machine Learning Engineer
•
System Design
•
medium
Design a system to detect credit card fraud during the checkout process. The system must block fraudulent transactions in real-time.
#Fraud Detection
#Real-time Inference
#Feature Store
Machine Learning Engineer
•
System Design
•
medium
Design a system to predict the optimal packaging box size for a multi-item order to minimize shipping costs and material waste.
#Optimization
#3D Bin Packing
#Regression
Machine Learning Engineer
•
Technical
•
medium
Write a SQL query to find the top 3 best-selling products in each category during the Big Billion Days sale, given a 'sales' and a 'products' table.
#Window Functions
#Aggregations
#Joins
Machine Learning Engineer
•
Technical
•
medium
How do you handle severe class imbalance when training a model to predict Return to Origin (RTO) for Cash on Delivery (COD) orders?
#Class Imbalance
#Loss Functions
#Sampling Techniques
Machine Learning Engineer
•
Technical
•
hard
Explain the architecture of a Two-Tower neural network. How do you perform negative sampling when training it for product retrieval?
#Deep Learning
#Information Retrieval
#Embeddings
Machine Learning Engineer
•
Technical
•
medium
What is the difference between NDCG and MAP? Which metric would you use to evaluate Flipkart's search engine and why?
#Evaluation Metrics
#Information Retrieval
Machine Learning Engineer
•
Technical
•
medium
How do you handle Out-Of-Vocabulary (OOV) words in NLP models, especially for Indian regional languages or transliterated Hindi (Hinglish)?
#NLP
#Tokenization
#Text Processing
Machine Learning Engineer
•
Technical
•
medium
Explain the self-attention mechanism in Transformers. How does it scale with sequence length?
#Deep Learning
#Transformers
#NLP
Machine Learning Engineer
•
Technical
•
hard
How would you design an A/B test to evaluate a new search ranking algorithm? What metrics would you track and how do you determine statistical significance?
#A/B Testing
#Experimentation
#Hypothesis Testing
Machine Learning Engineer
•
Technical
•
hard
You are processing 10TB of clickstream data in Apache Spark and encounter an OutOfMemory (OOM) error due to data skew. How do you fix it?
#Apache Spark
#Distributed Computing
#Data Skew
Machine Learning Engineer
•
Technical
•
hard
What is model quantization? How would you optimize a large PyTorch model to reduce inference latency on CPU instances?
#Model Deployment
#Optimization
#Quantization
Machine Learning Engineer
•
Technical
•
medium
Write a SQL query to calculate the 7-day rolling average of daily sales for each product.
#Window Functions
#Time Series
Machine Learning Engineer
•
Technical
•
easy
Explain the bias-variance tradeoff. How do regularization techniques like L1 and L2 affect this tradeoff?
#Fundamentals
#Regularization
Machine Learning Engineer
•
Technical
•
medium
How do you evaluate the quality of embeddings generated for Flipkart's product catalog before deploying them to production?
#Embeddings
#Evaluation
#Unsupervised Learning
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.