EmergingConversation, prompt and context designPart of The agent workforce

Context Engineer

Also called AI Context Engineer · Prompt/Context Architect

A Context Engineer decides what information, memory and tools reach the model at each step. That choice shapes answer quality, cost and privacy, so it decides whether an AI product is useful or merely impressive in a demo.

What they do

They work out what the model needs to know at each point in a conversation or task, and what it should never see. They design how documents are retrieved, trimmed and ordered, what gets remembered between sessions, and which tools are offered when. They write and version prompts, build dialogue prototypes, and run evaluation suites to see what changed. They test for leakage of private or irrelevant material and for answers that drift from the source. They trade coverage against cost, because every extra token has a price. Much of the week goes on reading failed outputs and tracing them back to the context.

What a strong hire delivers

In the first months, a strong hire maps how context is assembled today and finds where it wastes space or goes missing. They put in a versioned context pipeline with clear rules for selection and memory. They build grounding and leakage tests that run before each release. The team can then see whether a change helped. Cost per task and privacy exposure become things the company can measure and discuss.

How you can tell they are good

Ask for a real context pipeline they built and why they chose what went in and what stayed out. Strong people show failed cases, not just wins. They can explain how they measured relevance, what they did about private data, and how they decided a memory rule was working. Be wary of anyone who talks only about clever prompt wording and cannot describe a test.

Why it is hard to fill

The title is new and rarely appears on a CV. Most people doing the work are called prompt engineer, conversation designer, or simply AI engineer. Real scarcity sits in the mix: strong writing and structure sense, plus enough technical depth to handle retrieval, embeddings and evaluation. Engineers often lack the language instinct. Designers often lack the testing habit. Candidates with both are few, and they know it.

Where to find them

Look at conversation designers, content designers, linguists and application designers who have moved into model-facing work. Also look at prompt engineers and applied engineers who have built retrieval systems and evaluation suites. They sit mostly in AI startups and product companies shipping assistants or agents, often inside a product or applied AI team under another title. Search by what they built, not by title.

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 a Context Engineer

  1. Describe a context pipeline you built. What went into the model, what stayed out, and why?

    A strong answer names specific sources, selection rules and trade-offs, and shows how they checked relevance. Worry if they describe only prompt wording, or cannot say what they deliberately excluded.

  2. How have you decided what an assistant should remember between sessions, and what it should forget?

    Look for a clear memory policy covering usefulness, staleness, user consent and privacy. Strong candidates mention testing it. Worry if memory is simply everything kept, or if privacy comes up only when prompted.

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

Job description you can post

We are building AI products that depend on giving the model the right information at the right moment. We are hiring a Context Engineer to design what enters the model's context, including documents, memory and tools, and to prove it works with tests. You will work closely with engineering and product.

What you will do

  • Design how information, memory and tools are selected and assembled for model context
  • Write, version and maintain prompts and context templates
  • Build grounding and leakage tests and run them before releases
  • Run evaluation suites and use the results to guide changes
  • Balance context coverage against cost and privacy limits
  • Review failed outputs and trace them to context causes
  • Document context and memory policies for the wider team

What you will bring

  • Examples of context, prompt or dialogue systems you have designed and shipped
  • Evidence of evaluation-driven iteration, with tests you wrote
  • Working knowledge of retrieval and embeddings
  • Clear, precise writing that others can follow and reuse
  • Sound judgement on privacy and data exposure
  • Ability to explain trade-offs to engineers and non-technical colleagues

Nice to have

  • Background in conversation design, content design or linguistics
  • Experience with localisation across languages
  • Experience with agent frameworks and tool use

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

Skills that matter

  • Service and conversation designAdvancedStructure dialogue, escalation and service experiences
  • Prompt and context designAdvancedStructure instructions, examples and context for a task
  • Model evaluationWorkingMeasure capability and failure modes credibly
  • Linguistics and localisationWorkingAdapt language behaviour across cultural and linguistic contexts

Other roles in conversation, prompt and context design

Hiring nowConversation DesignerA Conversation Designer shapes how an AI service talks, asks, hands over and recovers. They turn model behaviour into dialogue people can finish…EmergingPrompt EngineerA Prompt Engineer writes and tests the instructions and examples that make a model do one task well. They turn vague prompting into versioned…Hiring nowAI Content DesignerAn AI Content Designer writes the words inside an AI product: prompts users see, explanations, warnings and error messages. Good content helps…

Related roles in other families

Hiring nowNatural Language Processing ScientistLanguage and multilingual intelligenceAn NLP Scientist builds and tests methods for language understanding and generation. They make sure a company's language models work across…Hiring nowMultilingual Model ResearcherLanguage and multilingual intelligenceA Multilingual Model Researcher improves how well a model transfers and behaves across languages. It matters because a product that works in one…Hiring nowLanguage Localisation EvaluatorLanguage and multilingual intelligenceA Language Localisation Evaluator judges whether model output means the right thing, sounds right and is appropriate in a specific locale. It…EmergingLow-Resource Language Data ResearcherLanguage and multilingual intelligenceA Low-Resource Language Data Researcher builds ethically sourced datasets and evaluations for languages that models serve poorly. 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.

← Conversation, prompt and context designAll new job families

Start a search

Hiring a Context 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.