← Amazon Interview Insights

Amazon·Machine Learning Engineer·Technical Phone Screen·Intermediate

Intermediate
Apr 2026

Summary

Had a technical phone screen for an ML Engineer role at Amazon. Just one question but it cut straight to the fundamentals, no warmup.

Questions Asked (1)

Q1

What is the difference between inference and training in machine learning?

Technical Trade-offsSystem Design
Author's notes

Seemed basic at first and I almost relaxed too much.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by defining both training and inference clearly, then contrast them across key dimensions like computational requirements, data flow, and objectives. Emphasize that training is a one-time (or periodic) heavy process to learn parameters, while inference is a lightweight, repeated process to apply those parameters to new data. Use examples to illustrate the differences and highlight trade-offs relevant to system design at scale.

Pro tip: At Amazon, interviewers value practical insights: mention how inference often requires optimization for latency and cost, while training focuses on throughput and convergence, and discuss how this impacts system architecture decisions.

1. Define Training

Explain that training involves feeding labeled data through a model to learn parameters (weights and biases) by minimizing a loss function, typically using backpropagation and gradient descent.

2. Define Inference

Describe inference as using the trained model to make predictions on new, unseen data, where the parameters are fixed and no learning occurs.

3. Compare Computational Aspects

Contrast the computational intensity: training requires significant resources (GPUs/TPUs, memory, time) for forward and backward passes, while inference is lighter, often optimized for low latency and high throughput.

4. Discuss Data and Objectives

Highlight that training uses large labeled datasets and aims to generalize well, whereas inference uses individual or small batches of unlabeled data and aims to produce accurate, fast predictions.

5. Relate to System Design Trade-offs

Explain how these differences influence system design: training may be done offline in batches, while inference is often online and real-time, requiring different infrastructure, scaling, and optimization strategies.

Key Points to Mention

  • Training learns parameters; inference uses fixed parameters.
  • Training is computationally heavy and iterative; inference is lightweight and often optimized for latency.
  • Training uses labeled data and backpropagation; inference uses new data and forward propagation only.
  • Training is typically done offline or periodically; inference is often real-time or near-real-time.
  • System design implications: training clusters vs. inference endpoints, batch vs. online processing, and cost/latency trade-offs.
  • Examples: training a model to classify images vs. serving that model to classify user-uploaded images.

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.