Tesla Machine Learning Engineer Interview Questions
Master your tech interview with our curated database of real questions from top companies.
Implement and vectorize NumPy Conv2D
Implement a 2D convolution operation from scratch using NumPy only (no TensorFlow or PyTorch). Assume NCHW input shape (N, C_in, H_in, W_in) and weigh...
Compare RNNs, LSTMs, Transformers, and MPC
Sequence Modeling Architectures and MPC (Technical Screen) You worked on a sequence-modeling project involving multivariate time-series signals and mu...
Implement automatic braking logic in Python
Using Python, implement a simple automatic braking function. Given current speed v (m/s), distance to obstacle d (m), maximum deceleration a_max (m/s^...
Compute Conv2D parameter counts
Parameter Count for a 2D Convolution Layer You are given a standard 2D convolution layer with: - Input channels: C_in - Output channels: C_out - Kerne...
Explain and derive importance sampling estimators
Importance Sampling: Estimators, Properties, Optimal Proposals, and ESS Context You want to estimate an expectation under a target distribution p over...
Implement attention and Transformer with backward pass
Implement Scaled Dot-Product Attention and a Transformer Block (No Autograd) Context: Build multi-head self-attention and a Transformer encoder-style ...
Compute nearest index within threshold after walking distances
You are given: ( 1) points: a list of N 2D coordinates in miles, points[i] = [x_i, y_i], ordered; ( 2) distances: a list of M nonnegative floats (mile...
Design an LLM math-solving chain
Design an LLM-Based Arithmetic Solver Context You are building an LLM-driven service that answers arithmetic questions ranging from simple expressions...