Design LLM-drafted recruiter outreach messages
PremiumLLM systemMedium
- LLM personalisation
- Grounded generation
- Reply rate metrics
Quick answer
This LLM system interview question asks you to design LLM-drafted recruiter outreach messages. Aim for a design that uses language models to serve users well, then explain retrieval, prompting, serving, evaluation and trade-offs. Interviewers want to see how you control quality, cost and latency, and how you evaluate the results.
The problem
Design LLM-drafted recruiter outreach messages: a writing assistant that drafts a personalised outreach message for each candidate a recruiter picks, from the candidate’s profile and the job’s needs. The hard parts are staying true to the profile, serving over 1 billion members without drafting for all of them, and measuring replies instead of volume.
A recruiter shortlists 25 candidates for a backend engineer role and clicks “Draft messages”. Each draft should name 2 or 3 real reasons this person fits, in the recruiter’s tone, and the recruiter reviews, edits and sends each one. Nothing is sent without the recruiter.
What must the system do?
- Draft on demand: Generate drafts only for candidates the recruiter has selected, one per candidate, streaming into the review screen.
- Grounded personalisation: Every statement about the candidate comes from a visible profile field; every statement about the job comes from the posting or the recruiter’s notes.
How well must it do it?
- Reply-based success: Success is reply rate and positive reply rate per message sent, with decline and spam-report rates as guardrails, not the number of messages sent.
- Latency: First words within 2 seconds; all 25 drafts of a batch complete within 30 seconds.
What scale should you design for?
Use these numbers in your estimates.
The scale numbers unlock with this questionUnlock
Key concepts
- LLM personalisation
- Grounded generation
- Reply rate metrics
- Prompt caching
- Protected attributes
- Prompt injection
How you’ll practise
- Problem framing
- Data and retrieval
- Prompting and orchestration
- Evaluation and safety
- Serving, cost and latency
- Wrap-up
Lala, personalized to you, gives a hint when you ask and reviews your design when you are ready.
What do interviewers look for?
In any LLM system design round.
- Defines the user task and what a good answer is
- Explains how relevant context reaches the model
- Plans evaluation before and after launch
- Controls cost and latency with caching and routing
- Covers safety, privacy and abuse
- Handles failures and fallbacks gracefully
Questions people ask about this interview question
- Which design type is this question?
- It is an LLM system question. You design LLM-drafted recruiter outreach messages and explain your choices the way you would in an interview.
- Is this question asked at entry level?
- It is marked Medium. Entry-level engineers can practise it, but it expects you to reason about requirements and trade-offs, not only list components.
- What should I cover first?
- Start with the user task, what a good answer looks like and how it will be measured. Agree on scope with the interviewer before you design anything.
- Can I practise it for free?
- It is a premium question. Sign up and unlock it once for 10 credits; it then stays unlocked. When you finish, Lala, your personalized AI mentor, can review your design for 30 credits.
Related questions
Updated · Written by the SevyDevy team