Binary Searchmedium45 minAI/ML Engineer

Embeddings Minimum Feasible Throughput

AI/ML Engineer signal: binary search on answer + monotonic predicate in a embedding drift monitor context. This is a ProdMatch-owned ai ml engineer drill, framed as a May 2026 SAP Labs Model Observability simulation, not a copied platform question.

Company context

SAP Labs · Model Observability

Freshness

May 2026

Product surface

embedding drift monitor

ProdMatch interview simulation based on product-team patterns; not a claim of a real company question.

Question

For embedding drift monitor, choose the minimum processing rate so all vectors finish before deadline. Each worker can process rate units per minute, rounded up per item.

Input

Work item sizes and deadline minutes.

Output

Minimum integer rate.

Constraints

1 <= items.length <= 200000
1 <= item size <= 1e9
Deadline is at least items.length.

Concepts

vector search
RAG retrieval
recommendation graphs
binary search on answer
monotonic predicate

sizes [3,6,7,11], deadline=8 -> 4

Approach

Try framing your own approach first. The 30 seconds you think before peeking is where learning happens.

Clean Solution

Reveal the approach first.

How well did you understand?

Your rating tunes when this problem shows up again.

Common Mistakes

Use low + (high - low) // 2 to avoid overflow.
The predicate must be monotonic or binary search is invalid.

Next Similar Problems

Vector Minimum Feasible Throughputmedium GraphRAG Minimum Feasible Throughputmedium Recommend Minimum Feasible Throughputmedium