AI/ML Engineer signal: shortest path + weighted graph in a learning-to-rank pipeline context. This is a ProdMatch-owned ai ml engineer drill, framed as a April 2026 Practo Search ML simulation, not a copied platform question.
Company context
Practo · Search ML
Freshness
April 2026
Product surface
learning-to-rank pipeline
ProdMatch interview simulation based on product-team patterns; not a claim of a real company question.
In learning-to-rank pipeline, entities are connected by weighted evidence edges. For each query, find the least-cost evidence path from source to target while avoiding blocked entities.
Input
Output
Constraints
Concepts
0-1 cost 2, 1-2 cost 3, query 0->2 -> 5
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.