← Waymo Interview Insights

Waymo·Data Scientist·Technical Phone Screen·Senior

Senior
Jul 2026

Summary

Waymo data science interview with a meaty stats/ML problem centered on trajectory analysis. The whole session was basically one long case question with a follow-up baked in. Felt more like a research discussion than a traditional interview.

Questions Asked (2)

Q1

You have drone-captured 2D turning trajectories from vehicles at multiple intersections, some from Waymo autonomous vehicles and some from others. How would you statistically test whether Waymo's turning behavior is meaningfully different from the rest of the population? Walk through your feature choices, distributional assumptions, test selection, and how you'd report effect size.

A/B Testing & ExperimentationProduct Analytics & MetricsTechnical Trade-offs
Author's notes

This is a deceptively open question.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Frame the problem as a two-sample comparison of turning trajectory distributions, where each trajectory is represented by engineered features capturing geometry, dynamics, and variability. Choose statistical tests that respect the nested structure (multiple turns per intersection) and non-normal, multimodal nature of trajectory data, then report both significance and practical effect sizes with confidence intervals.

Pro tip: Emphasize that statistical significance alone is insufficient; Waymo cares about safety-relevant, actionable differences. Use effect sizes like Cohen's d or overlap coefficient and relate them to real-world implications (e.g., collision risk, comfort).

1. Feature Engineering

Extract interpretable features from each 2D turning trajectory: turn radius, curvature profile, entry/exit speed, acceleration, jerk, steering angle rate, path length, and lateral deviation from a reference path. Also compute distributional summaries per intersection (mean, variance, skewness) to capture variability.

2. Distributional Assumptions & Data Exploration

Plot distributions (histograms, KDEs) and test normality (Shapiro-Wilk, Anderson-Darling). Expect non-normal, possibly multimodal distributions due to different turn types (left vs right, intersection geometry). Consider transformations or non-parametric methods.

3. Test Selection

For independent samples, use Mann-Whitney U or Kolmogorov-Smirnov for univariate features; for multivariate, use energy distance or maximum mean discrepancy (MMD). Account for clustering by intersection using mixed-effects models or cluster-robust standard errors. If comparing multiple features, control FDR (Benjamini-Hochberg).

4. Effect Size & Practical Significance

Compute Cohen's d, Cliff's delta, or overlap coefficient for each feature. For multivariate, use distance between distributions (e.g., energy distance) and permutation tests for p-values. Report confidence intervals via bootstrap.

5. Reporting & Interpretation

Present results with clear visualizations (e.g., violin plots, trajectory overlays) and a table of effect sizes with CIs. Discuss whether differences are safety-relevant, consistent across intersections, and robust to confounders (e.g., turn type, speed limit).

Key Points to Mention

  • Nested data structure: multiple trajectories per intersection, requiring hierarchical or cluster-robust methods.
  • Non-normal and multimodal distributions: use non-parametric tests or resampling methods.
  • Multivariate comparison: energy distance or MMD to compare full trajectory distributions.
  • Effect size metrics: Cohen's d, Cliff's delta, overlap coefficient, and their interpretation.
  • Multiple testing correction: Benjamini-Hochberg FDR to control false discoveries across features.
  • Confounders: turn direction, intersection geometry, speed limit, and traffic conditions.

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

Q2

Traffic volume and driving patterns vary across intersections. How do you prevent intersection-level confounding from distorting your Waymo vs. other vehicles comparison, and what modeling approach would you use?

A/B Testing & ExperimentationData ModelingTechnical Trade-offs
Author's notes

I blanked for a second here because I'd been so focused on the trajectory representation piece.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Acknowledge intersection-level confounding as a key threat to validity, then propose a mixed-effects modeling framework that accounts for both fixed effects (e.g., vehicle type) and random effects (e.g., intersection-level intercepts and slopes). Emphasize the importance of controlling for time-varying and static intersection characteristics, and discuss how to validate the model and interpret results in the presence of confounding.

Pro tip: Frame the problem as a hierarchical data structure where observations are nested within intersections, and highlight that random slopes for vehicle type allow the treatment effect to vary by intersection—this shows you understand both the statistical nuance and the practical need for generalizable insights.

1. Identify and measure confounders

List intersection-level factors (e.g., traffic volume, road geometry, signal timing, weather, time of day) that could correlate with both vehicle type presence and outcome metrics. Ensure these are captured in the data or can be proxied.

2. Choose a modeling strategy

Propose a mixed-effects model (or hierarchical model) with random intercepts for intersections to account for unobserved heterogeneity, and consider random slopes for vehicle type if the effect is expected to vary across intersections.

3. Control for observed confounders

Include fixed effects for key intersection-level covariates (e.g., traffic volume, number of lanes) and temporal factors (e.g., hour of day, day of week) to adjust for measured confounding.

4. Validate and diagnose the model

Check for overfitting, convergence issues, and residual confounding using cross-validation, posterior predictive checks, or sensitivity analyses. Compare with simpler models to justify complexity.

5. Interpret and communicate results

Explain how the model isolates the Waymo vs. other vehicles effect while accounting for intersection variability. Discuss limitations and potential for unmeasured confounding, and suggest robustness checks.

Key Points to Mention

  • Mixed-effects models with random intercepts and slopes for intersections
  • Fixed effects for intersection-level covariates (traffic volume, road type, etc.)
  • Temporal controls (time of day, day of week) to account for driving pattern variations
  • Model validation techniques (cross-validation, sensitivity analysis)
  • Interpretation of variance components and intraclass correlation coefficient (ICC)
  • Potential for unmeasured confounding and how to assess robustness

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