TikTok·Machine Learning Engineer·Technical Phone Screen
Apr 2026
TikTok ML Engineer interview that went pretty deep into the weeds on model diagnostics and transformer internals. Four meaty questions, not a lot of fluff, and they clearly wanted you to go beyond surface-level definitions.
- How do you diagnose and mitigate overfitting in ML models? Walk through the trade-offs of techniques like regularization, dropout, early stopping, data augmentation, architecture changes, and cross-validation.
- How do you handle class imbalance? Compare undersampling, oversampling (including SMOTE and its variants), class weighting, focal loss, and threshold adjustment, and explain how you'd evaluate performance under each approach.
- Walk me through common undersampling strategies, specifically random undersampling, Tomek links, Edited Nearest Neighbors, NearMiss variants, and cluster centroid methods. How does each affect bias, variance, and minority class recall?
- What is an attention head? Explain queries, keys, and values, how multi-head attention splits the representation space, what different heads tend to capture, and how the number of heads affects model capacity and compute.
“I started with the obvious stuff, L1 vs L2, and the interviewer just nodded and waited.” The rest of the author's notes on Machine Learning Engineer interview at TikTok, Technical Phone Screen round, covers how they worked through the question, what the panel pushed back on, and what they would do differently.
View Post