Top 17
Prep plan
Updated weekly · Last refresh Oct 17

Waymo Research Scientist Interview Questions

The questions to prepare for a Waymo Research Scientist interview. Questions from real interview reports rank first. Updated daily.

17questions
~4htotal time
Track your progressSign up free to work through all 17 questions and resume where you left off.
Start practicing free →
1
CodingStart here. 7 questions · ~99 min
Top K Closest Obstacles StreamMedium
Practice
Recently asked

Use a heap-based priority queue to keep the k closest obstacle readings from a sensor stream.

priority queuesensor datatop kWaymo
Implement Binary Focal Loss GradientsHard
Practice
Recently asked

Implement numerically stable binary focal loss and its backward pass from logits, including reduction handling.

backpropagationloss functionsnumpyWaymo
Minimum Cost Multi-Stage RouteMedium
Practice
Recently asked

Use dynamic programming with two rolling states to minimize total cost across stages with stay-or-switch decisions.

space complexitytime complexityDynamic ProgrammingWaymo
More Coding questions with a free account
2
System Design4 questions · ~56 min
Design an Edge Case Mining PipelineHard
Recently asked

Design an ML pipeline that mines rare autonomous driving edge cases from fleet logs and prioritizes high value segments for labeling.

fleet dataactive learningdata ingestionWaymo
Trajectory Prediction and EvaluationHard
Recently asked

Design a multi-trajectory behavior prediction system for surrounding vehicles and define how to evaluate it.

fleet dataModel Servingfailure modesWaymo
More System Design 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
Machine Learning3 questions · ~42 min
Fast Image ConvolutionHard
Recently asked

Choose the fastest practical method for image convolution and justify the tradeoffs between direct, separable, and FFT-based implementations.

optimizationWaymo
Zero-Shot Learning ApproachHard
Recently asked

Explain how to build and evaluate a zero-shot learning system for classes never seen during training.

model choicemodel fine-tuningModel EvaluationWaymo
Patchify and Train EncoderHard
Recently asked

Design a patch-based image encoder and explain how to train it effectively on unlabeled images.

Feature EngineeringDeep Learningmodel trainingWaymo
4
Behavioral & Leadership3 questions · ~42 min
More Behavioral & Leadership questions with a free account
The finish line: interview-readyComplete all 17 questions to finish this plan.