AI/ML Engineer signal: binary search on answer + monotonic predicate in a beam-search decoder context. This is a ProdMatch-owned ai ml engineer drill, framed as a May 2026 NoBroker GenAI Runtime simulation, not a copied platform question.
Company context
NoBroker · GenAI Runtime
Freshness
May 2026
Product surface
beam-search decoder
ProdMatch interview simulation based on product-team patterns; not a claim of a real company question.
For beam-search decoder, choose the minimum processing rate so all tokens finish before deadline. Each worker can process rate units per minute, rounded up per item.
Input
Output
Constraints
Concepts
sizes [3,6,7,11], deadline=8 -> 4
Try framing your own approach first. The 30 seconds you think before peeking is where learning happens.
Reveal the approach first.
Your rating tunes when this problem shows up again.