LinkedIn·Data Scientist·Technical Phone Screen
Jun 2026
LinkedIn data scientist interview that went deep into the math. One question, no fluff, they wanted you to actually write out the backprop derivation on the spot, not just talk about it in vague terms.
- Derive backpropagation from scratch for a feed-forward neural network. Walk through the forward pass equations (linear transformation plus activation at each layer), define the loss, then use the chain rule to derive the weight and bias gradients for each layer. Write out the actual math.
“This is the kind of question where nodding along in study sessions does not prepare you.”