Perplexity ML / LLM design interview

Round 5 of 7 · 3 questions reported

See the whole loop
Length
60 min
Format
Design discussion
They grade
How an LLM product works end to end: retrieval, model serving, search quality, citations
Heads-up
Reported in some loops, not all.

Questions Perplexity asks in this round 3

  • Design a feed recommendation systemML designRank the items in each user's home feed so they engage more, choosing from millions of candidates within a couple of hundred milliseconds.
    Possibly retired
  • Design a RAG system over company docsAI systemEmployees should be able to ask questions about internal documents (Drive, Confluence, Slack, GitHub) and get grounded answers with citations.
  • Design an answer engine with citationsAI systemDesign an answer engine: a user asks a question in plain language and gets a direct, current answer written by a model, with numbered citations to the web pages it used, streaming…