Loading…
Beam Search Decoder is a hard coding interview question covering nlp, deep learning, dynamic programming — the kind asked at FAANG (Facebook/Meta, Apple, Amazon, Netflix, Google) and AI-first companies like Anthropic, OpenAI, and Nvidia.
Implement beam search for sequence decoding, used in machine translation, speech recognition, and LLM token generation.
Given: beam_width k, a scoring function next_token_logprobs(sequence) -> list of (token, log_prob) pairs, max_len, and EOS token.
At each step: 1. Expand each of the k beams by all possible next tokens 2. Score each candidate as cumulative_logprob + new_logprob 3. Keep top-k by total score 4. Stop when all beams hit EOS or max_len
Return the best complete sequence.
Solution walkthrough on Pro
Upgrade to Pro to unlock the guided hints, the step-by-step walkthrough, solutions in Python, C++, Java, and Go, and complexity analysis.
What's inside this guide
Fully unlocked, no account needed — solutions, walkthroughs and follow-up answers included.
Or start the Study Plan — a week-by-week order for your loop, and week 1 is entirely free.
A full interview loop is more than one round. These are the others, each with what is on the site for it.