Prompt Engineer (LLM Systems, Evals & Safety)
At a glance
Mid-level AI Engineering role at webook.com. Remote, Jordan.
Pay not stated AI Engineering salary
remoteroles summary, based on the employer's posting.
What you'll do
- Write and refine prompts, system rules and tool instructions for different tasks
- Build evaluation setups with rubrics, reference answers and measures for model quality
- Maintain versioned prompt collections, run comparisons and track their performance
- Limit fabricated answers through verification, constrained outputs and tool use
- Test for jailbreaks, prompt injection, policy violations and mishandling of personal data
What you bring
- You have designed prompts for multiple kinds of tasks and models
- You have built evaluation datasets and automated scoring for quality, usefulness and cost or speed
- You understand retrieval-augmented generation and tool or function calling
- You can use Python or TypeScript for preparing data, evaluations and analysis
- You write clearly and turn business goals into prompt requirements that can be measured
Who this fits
This mid-level role suits someone focused on prompt design, evaluation and safety who can work with engineers to put prompts into production. It is remote and based in Amman, Jordan.
From the employer
Do you want to love what you do at work? Do you want to make a difference, an impact, and transform peoples lives? Do you want to work with a team that believes in disrupting the normal, boring, and average?
If yes, then this is the job you are looking for , webook.com is Saudi’s #1 event ticketing and experience booking platform in terms of technology, features, agility, revenue serving some of the largest mega events in the Kingdom surpassing over 2 billion in sales.
Role Overview
Design high-quality prompts, system instructions, and tooling that make our LLM features accurate, safe, and cost-effective. You’ll own evaluation, prompt versioning, and continuous improvement.
Key Responsibilities:
- Author, refactor, and chain prompts (system/tool/policy) for varied tasks.
- Create offline/online evaluation harnesses (rubrics, golden sets, metrics).
- Build prompt libraries with versioning, A/B testing, and telemetry.
- Reduce hallucinations via verification, constrained decoding, and tool use.
- Implement safety: jailbreak/prompt-injection tests, content policy checks, PII handling.
- Partner with engineers to integrate prompts into production features.
Requirements
- Demonstrated prompt design across multiple task types and models.
- Experience building eval datasets and automated scoring (e.g., accuracy, faithfulness, utility, cost/latency).
- Familiarity with retrieval-augmented generation concepts and tool/function calling.
- Strong scripting (Python/TypeScript) for data prep, evals, and analysis.
- Clear writing; ability to translate business goals into measurable prompt specs.
Nice-to-Haves
- Experience with LangChain/LLM orchestration, vector stores, and rerankers.
- Knowledge of safety tooling and red-teaming techniques.
- Experiment platforms (feature flags, A/B tests), analytics.