Top 25
Prep plan
Updated weekly · Last refresh Sep 22

Infosys Computer Vision Engineer Interview Questions

The questions to prepare for a Infosys Computer Vision Engineer interview. Questions from real interview reports rank first. Updated daily.

25questions
~3htotal time
Track your progressSign up free to work through all 25 questions and resume where you left off.
Start practicing free →
1
System DesignStart here. 4 questions · ~32 min
Design On-Device Model OptimizationMedium

Design an on-device ML optimization system that balances model quality, latency, memory, power, and rollout safety on mobile hardware.

InfrastructureFeature StoreModel ServingInfosys
Research to Production Model TransitionHard

Assesses practical experience moving vision models into production systems.

production deploymentInfosys
Automated Medical Image Analysis PipelineHard

Assesses system design trade-offs between accuracy and latency for medical image analysis.

pipeline designAccuracyInfosys
More System Design questions with a free account
2
Machine Learning17 questions · ~136 min
CNNs vs Transformers for VisionMedium

Compare CNN and Transformer architectures for vision, and explain when each is the better model choice.

Neural NetworksFeature EngineeringDeep LearningInfosys
Tune Production Model HyperparametersMedium

Choose hyperparameters for a production model using cross-validation, regularization, and held-out evaluation.

Hyperparameter TuningCross-ValidationFeature EngineeringInfosys
Vanishing Gradients in Deep NetworksMedium

Explain vanishing gradients in deep networks and how residual connections, batch normalization, and activation choice improve training.

Neural NetworksDeep LearningGradient DescentInfosys
Real-Time Edge Inference OptimizationHard

Tests ability to reduce latency and compute while maintaining vision model quality on edge hardware.

edge devicesInfosys
More Machine Learning questions with a free account

Sign up to see every question

Create a free account to unlock this list and practice real interview questions.

Get my prep plan
3
Behavioral & Leadership4 questions · ~32 min
Production Model Failure RecoveryHard

Tests ownership during an ML production failure, including diagnosis, cross-functional communication, and learning from offline-vs-production gaps.

production failuremodel trainingDebuggingInfosys
More Behavioral & Leadership questions with a free account
The finish line: interview-readyComplete all 25 questions to finish this plan.