← Uber Interview Insights

Uber·Machine Learning Engineer·Technical Phone Screen·Intermediate

Intermediate
Apr 2026

Summary

Interviewed for an ML engineer role at Uber and got hit with a computer vision fundamentals question. Pretty short session from what I remember, nothing too crazy but it did make me realize how rusty I was on the theory side.

Questions Asked (1)

Q1

Can you explain what semantic segmentation is and how it works?

Technical Trade-offsAlgorithms & Data Structures
Author's notes

I knew the gist of it, assigning a class label to every pixel in an image rather than just drawing a bounding box around objects.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start with a clear, concise definition of semantic segmentation, then explain the typical architecture (e.g., encoder-decoder with skip connections) and how it assigns a class label to each pixel. Emphasize the role of loss functions (e.g., cross-entropy) and mention common evaluation metrics like IoU. Tailor the explanation to Uber's scale by discussing trade-offs in model efficiency and real-time inference.

Pro tip: Connect semantic segmentation to Uber's use cases like autonomous driving or map enhancement, showing you understand the business impact. Also, mention recent advancements like transformers or efficient architectures (e.g., MobileNet) to demonstrate up-to-date knowledge.

1. Define semantic segmentation

Explain that it's a computer vision task where each pixel in an image is classified into a predefined category, unlike object detection which uses bounding boxes.

2. Describe the architecture

Outline the encoder-decoder structure: the encoder extracts features and reduces spatial dimensions, while the decoder upsamples to restore resolution, often with skip connections (e.g., U-Net) to retain fine details.

3. Explain training and loss

Mention that models are trained with pixel-wise cross-entropy loss, sometimes combined with Dice loss for class imbalance. Discuss how ground truth masks are used.

4. Discuss evaluation and trade-offs

Cover metrics like IoU and pixel accuracy, and trade-offs between accuracy and inference speed, especially for real-time applications at Uber.

5. Relate to Uber's context

Connect to Uber's needs: autonomous vehicle perception, mapping, or food delivery image analysis, highlighting scalability and efficiency considerations.

Key Points to Mention

  • Difference between semantic and instance segmentation
  • Encoder-decoder architectures (e.g., U-Net, FCN, DeepLab)
  • Skip connections for preserving spatial information
  • Loss functions: cross-entropy, Dice loss, focal loss
  • Evaluation metrics: IoU, pixel accuracy, mean IoU
  • Real-time constraints and model optimization (e.g., quantization, pruning)

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