Snap·Machine Learning Engineer·Technical Phone Screen
May 2026
Snapchat ML Engineer interview that went deep on neural network fundamentals. Three main areas: loss functions, optimizers, and architectures, each with follow-up questions that pushed pretty far below the surface. Not a vibe check, they actually wanted to see if you understood the math.
- Walk me through the main loss functions used in regression and classification. When would you pick one over another, and what does the gradient behavior look like for each?
- How do contrastive and triplet losses work, and when would you reach for a ranking loss instead of a standard classification objective?
- Compare SGD with momentum, RMSProp, and Adam. What are the practical tradeoffs in terms of convergence speed and how they affect generalization?
- Explain learning rate schedules: warmup, cosine decay, and step decay. Why does warmup matter at the start of training?
- Describe how self-attention works in a Transformer, including multi-head attention and positional encoding. Why do we need positional encoding at all?
- When would you use a CNN versus an RNN versus a Transformer for a sequence modeling problem?
“This started easy enough, MSE versus MAE, then they asked about Huber and I fumbled a bit explaining the transition point between the two regimes.” The rest of the author's notes on Machine Learning Engineer interview at Snap, 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