← LinkedIn Interview InsightsAI Engineer

LinkedIn·AI Engineer·Onsite - System Design / Architecture·Senior

Senior
May 2026

Summary

LinkedIn AI Engineer system design round, one big open-ended question about building a personalized InMail generation system from scratch. The scope was genuinely wide and I kept second-guessing how deep to go on each layer.

Questions Asked (1)

Q1

Design an AI-powered personalized InMail system that helps recruiters send tailored outreach messages to candidates, covering the full stack: recruiter UI, context retrieval, prompt engineering and LLM serving, personalization signals, delivery and tracking, feedback loops for model improvement, and considerations around latency, cost, abuse prevention, and PII.

System DesignTechnical Trade-offsProduct Sense & Ideation
Author's notes

This one sprawls in every direction and I spent the first few minutes just trying to figure out where to even start.

Create a free account to read the full note

AI HintsAI Generated

Suggested Approach

Start by clarifying the product goals and constraints (e.g., recruiter workflow, candidate experience, compliance), then walk through the system end-to-end: recruiter UI, context retrieval, LLM serving, personalization, delivery/tracking, and feedback loops. Emphasize trade-offs in latency, cost, abuse prevention, and PII handling, and propose a phased rollout with metrics.

Pro tip: Anchor your design around a human-in-the-loop workflow where recruiters can edit AI-generated drafts, and highlight how you'd measure success (e.g., reply rate, recruiter time saved) while guarding against spam and bias.

1. Clarify requirements and constraints

Ask about scale (number of recruiters, messages/day), latency targets, cost budget, compliance (GDPR, PII), and integration with existing LinkedIn systems. Define success metrics like reply rate, recruiter efficiency, and candidate satisfaction.

2. Design the recruiter UI and workflow

Outline a UI where recruiters select candidates, see AI-generated drafts with personalization highlights, and can edit/approve. Include controls for tone, length, and compliance checks, and ensure transparency about AI involvement.

3. Architect context retrieval and personalization

Describe how to fetch candidate data (profile, activity, mutual connections) and recruiter context (job description, company info) via internal APIs, then compute personalization signals (e.g., shared skills, recent posts) to feed the prompt.

4. Implement LLM serving and prompt engineering

Explain prompt construction with system instructions, few-shot examples, and retrieved context. Discuss model choice (fine-tuned vs. off-the-shelf), serving infrastructure (caching, batching), and guardrails (output validation, PII redaction).

5. Cover delivery, tracking, and feedback loops

Detail how messages are sent (via existing InMail pipeline), tracked (opens, replies), and how feedback (recruiter edits, candidate responses) is collected to improve prompts/models. Include abuse prevention (rate limits, spam detection) and PII handling.

Key Points to Mention

  • Human-in-the-loop: recruiters review and edit AI drafts to ensure quality and reduce risk.
  • Personalization signals: use candidate profile, activity, and mutual connections to tailor messages.
  • Latency and cost trade-offs: caching, batching, and model selection (e.g., smaller models for drafts, larger for refinement).
  • Abuse prevention: rate limiting, spam detection, and content moderation to protect candidates.
  • PII handling: redaction, encryption, and compliance with privacy regulations.
  • Feedback loops: collect recruiter edits and candidate responses to fine-tune models and improve prompts.

AI-generated suggestions, not part of the candidate's original notes. May be inaccurate — verify before relying on them.