EmergingTool-using agents and workflow orchestrationPart of The agent workforce

Agent Memory and Personalisation Engineer

Also called Agent Memory & Personalisation Engineer · Long-term Memory Engineer

Builds the memory, user models and personalisation layers that let an agent remember people across sessions and act on it. It matters because an assistant that forgets, or remembers badly, loses trust quickly.

What they do

Designs what an agent should remember, how it is stored and when it is recalled. Builds write and retrieval paths over vector and graph stores, decides what gets summarised, updated or forgotten, and keeps user models current as preferences change. Works with application and orchestration engineers so memory feeds tool use and planning. Sets privacy rules for what is kept, who can see it and how users delete it. Builds evaluations that show whether memory helps or causes stale, wrong or intrusive behaviour. Debugs cases where the agent recalled the wrong thing.

What a strong hire delivers

A working memory layer in production with clear rules on what is stored, recalled and deleted. A user model that improves responses in ways the team can measure. Evaluations that catch stale or wrong recall before users do. Privacy controls that legal and security can sign off. Documentation that lets other engineers add new memory types without breaking existing ones.

How you can tell they are good

Ask them to walk through a memory system they built and where it failed. Strong candidates describe wrong recall, stale facts and contradictions, and what they changed. Ask how they tested personalisation without relying on opinion. Ask how deletion works end to end. Worry if they talk only about vector search and never about forgetting, consent or evaluation.

Why it is hard to fill

Almost nobody has this title. The work usually sits inside application, search or platform roles, so CVs rarely signal it. Scarcity is high because the mix is unusual: retrieval skill, agent behaviour and privacy engineering. Search and recommendation engineers overlap strongly but may not have worked with language model agents. Candidates with real production memory experience are often at consumer products and rarely looking.

Where to find them

Look at application engineers, workflow automation builders and systems integrators who moved into agent work. Search, ranking and recommendation engineers are a strong adjacent pool. Privacy engineers who have worked on data retention are worth a conversation. Most come from consumer AI products and assistant teams, where long-term memory became a real problem first. Titles often read as backend, ML engineer or applied AI.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for an Agent Memory and Personalisation Engineer

  1. Describe a memory system you built for an agent or assistant. What did it store, and what did you choose not to store?

    Strong answers name concrete memory types, a clear reason for exclusions and the trade-offs involved. Look for privacy and usefulness both being considered. Worry if everything is stored by default or the answer is only about the database.

  2. How do you decide when a remembered fact is stale or wrong, and what should the agent do about it?

    Good answers cover timestamps, confidence, contradiction handling, asking the user and decay. They give examples. Worry if they assume stored facts stay true or have no update path.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are building an agent that remembers people and acts on what it knows. We need an engineer to own how that memory is created, stored, recalled and removed. You will work with application, orchestration and security colleagues to make personalisation useful, safe and measurable.

What you will do

  • Design and build persistent memory and user models for our agents
  • Build write, retrieval and consolidation paths over vector and graph stores
  • Decide what is remembered, updated and forgotten, and document the rules
  • Build evaluations that test memory quality and personalisation impact
  • Work with security and legal on privacy, consent and deletion
  • Debug wrong or stale recall in production and fix the cause
  • Help orchestration engineers use memory in tool-using workflows

What you will bring

  • Built and shipped a memory or personalisation system used by real users
  • Hands-on experience with retrieval, vector or graph databases
  • Experience designing evaluations for model or agent behaviour
  • Working knowledge of privacy engineering, including retention and deletion
  • Comfortable integrating with tools and agent frameworks
  • Clear written explanations of design trade-offs

Nice to have

  • Background in search, ranking or recommendation systems
  • Experience with security review of agent systems
  • Work on consumer assistants or similar products

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Agent orchestrationWorkingCoordinate tool-using agent execution
  • Tool and protocol integrationWorkingConnect models to external data and capabilities
  • Security engineeringWorkingProtect systems, identities and sensitive assets
  • Model evaluationWorkingMeasure capability and failure modes credibly

Other roles in tool-using agents and workflow orchestration

Hiring nowAI Agent EngineerAn AI Agent Engineer builds software agents that take real actions through tools they are explicitly permitted to use. They turn model capability…Hiring nowAgent Tool Integration EngineerAn Agent Tool Integration Engineer connects AI agents to outside systems through tightly scoped interfaces. They make sure agents act only where…EmergingAgent Workflow ArchitectAn Agent Workflow Architect decides which tasks go to agents, which stay with people, and where approvals sit. It matters because agents that act…EmergingComputer-Use Agent EngineerA Computer-Use Agent Engineer builds agents that operate real application interfaces, clicking, typing and reading screens, within firm limits. They…EmergingAI Agent ManagerAn AI Agent Manager assigns work to AI agents, reviews what they produce, handles the exceptions and tunes the workflow. They make agents dependable…

Related roles in other families

EmergingMulti-Agent Systems ResearcherMulti-agent coordination and economicsA Multi-Agent Systems Researcher studies how several AI agents behave when they work together, and builds methods and benchmarks to make that…EmergingAgent Coordination EngineerMulti-agent coordination and economicsAn Agent Coordination Engineer builds the layer that lets several AI agents hand work to each other, share state and settle conflicts. It matters…EmergingMulti-Agent Evaluation ScientistMulti-agent coordination and economicsA Multi-Agent Evaluation Scientist measures how groups of AI agents behave together and designs tests that expose collusion, cascades and…EmergingAgent Market Mechanism ResearcherMulti-agent coordination and economicsThis person designs and tests the rules that govern how AI agents trade, bid and share resources in bounded simulated markets. It matters because…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← Tool-using agents and workflow orchestrationAll new job families

Start a search

Hiring an Agent Memory and Personalisation Engineer?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.