JPJobPrepfull-stack interview
RoadmapsJS CompilerStar on GitHub

Career roadmap

Prompt Engineer

Design, test, and maintain the instructions that drive a model — and prove the changes worked with evaluations.

Time
3-5 months part-time
Entry bar
Open to writers, domain experts, testers, and analysts — not only developers.
Stages
5 · 21 topics
0/21 studied0%

Before you start Prompt Engineer

  • Precise written English
  • Systematic thinking: change one variable at a time
  • Spreadsheets
  • Enough Python or notebook comfort to run a script

How models behave

2-3 weeks · 0/3 topics

Understand the machine you are instructing.

  1. The unit of cost and the ceiling on input, in one concept.

    Ch 77 — LLM Fundamentals
    • Tokenisation quirks
    • Context window budgeting
    • Truncation behaviour
  2. Know what makes output vary before you blame the prompt.

    • Temperature and top-p
    • Repeated runs on one prompt
    • Seeds and why they are not enough
  3. A prompt is a per-model artefact. Scaffolding written for an older model over-applies on a newer one.

    • Capability tiers
    • Instruction-following differences
    • Refusal behaviour
    • Re-baselining after an upgrade

BuildA side-by-side comparison of one task across three models, with notes on where each fails.

Prompt patterns

3-4 weeks · 0/5 topics

Move from lucky prompts to reusable structure.

  1. The four-part skeleton behind almost every production prompt.

    Ch 78 — Prompt Engineering
    • Ordering for cacheability
    • Constraints over pleading
    • Fallback instruction for missing data
  2. Show the format you cannot describe. Vary the examples deliberately.

    • Example selection
    • Coverage of edge cases
    • Cost of examples in every call
  3. Two cheap focused calls usually beat one clever prompt.

    • Splitting classify-then-write
    • Routing with a cheap model first
    • Where chains add failure modes
  4. If code will parse it, constrain it with a schema.

    • JSON schema and enums
    • Validation as a normal error path
    • Why prefill tricks are gone
  5. Tag the data so instructions inside it read as content, not commands.

    • XML tags
    • Explicit 'this is untrusted' framing
    • Escaping user content

BuildA prompt library of ten task templates, each with inputs, output schema, and known failure cases.

Evaluation

4-6 weeks · 0/5 topics

This is the whole job. Opinions about prompts are worthless without measurement.

  1. Write scoring rules a second person can apply and reach your answer.

    • Binary criteria over 1-5 vibes
    • Inter-rater agreement
    • Rubric drift over time
  2. 50-200 frozen cases, including every failure you have personally seen.

    Ch 85 — Evaluation & Hallucination
    • Sourcing real cases
    • Covering edge cases
    • Keeping the set frozen for comparability
  3. Humans and models both judge A-vs-B far more reliably than absolute scores.

    • Blind comparison
    • Position bias
    • Win rate and ties
  4. Scale scoring with a model, then audit the judge against human labels.

    • Judge prompt design
    • Spot-check sampling
    • Known judge biases
  5. A 2-point win on 40 cases is nothing. Know when to believe a result.

    • Sample size intuition
    • Repeat runs and variance
    • Reporting uncertainty honestly

BuildAn eval report that recommends one prompt over another and shows why the difference is not noise.

Prompts inside systems

4-6 weeks · 0/4 topics

Prompts in production are code: versioned, cached, and budgeted.

  1. Every prompt has an id and a version, and both appear in the logs.

    • Prompt as a stored artefact
    • Attributing a regression to an edit
    • Rollback procedure
  2. Order the prompt so the stable part caches and the volatile part comes last.

    Ch 87 — Cost & Latency Optimization
    • Prefix stability
    • Verifying cache reads in usage
    • Trimming dead instructions
    • Output token caps
  3. In a RAG app, the retrieved context is most of the prompt. Its order and framing matter.

    Ch 80 — RAG Pipeline
    • Chunk ordering
    • Deduplicating context
    • Token budget per section
  4. A tool description is a prompt. Vague ones cause the wrong tool to fire.

    Ch 81 — Tool / Function Calling
    • Naming and when-to-use guidance
    • Parameter descriptions
    • Testing tool selection

BuildA versioned prompt config in a real repo, with cost per call before and after your trimming.

Safety & handoff

2-4 weeks · 0/4 topics

Break your own prompts before a user does, then hand them over cleanly.

  1. Assume any text from outside your system is trying to give orders.

    Ch 86 — AI Security
    • Direct and indirect injection
    • Data/instruction separation
    • Output validation before action
  2. Run a fixed attack suite on every prompt change, like a test suite.

    • Common attack shapes
    • Regression suite of attacks
    • Reporting severity honestly
  3. Prompts get logged. Decide what may never be in them.

    • Redaction before send and before log
    • Retention windows
    • Least-context principle
  4. A prompt only you can maintain is a single point of failure.

    • Documenting intent and failure cases
    • Eval instructions for the next owner
    • Ownership and review cadence

BuildA red-team report against your own app: attacks tried, which worked, the fix for each.

Prompt Engineer tools on your CV

  • Model playgrounds / Anthropic Console
  • A notebook or script runner
  • Git
  • Promptfoo or a custom harness
  • Langfuse
  • Spreadsheets

What Prompt Engineer employers ask to see

  • A public eval report with a recommendation and a noise analysis
  • A prompt library with documented failure cases
  • A red-team write-up

Read this honestly: the standalone title is shrinking. The work is being absorbed into AI engineer, applied AI, solutions engineer, and AI QA roles. Learn it as a specialism inside one of those, not as your only skill — it is still the most accessible on-ramp into AI work.

Content last reviewed 2026-08-31. Guidance only — no institute or paid placement is endorsed anywhere in this book.