Prompt Engineer (LLM Systems, Evals & Safety)

🏢 webook.com
📍 Amman, JordanRemote
📅 Posted: 7mo ago🔄 Updated: 7mo ago
CV%
✨ AI Summary
Prompt Engineer (LLM Systems, Evals & Safety) role responsible for designing high-quality prompts, system instructions, and tooling to ensure accurate, safe, and cost-effective LLM features. You will own evaluation, prompt versioning, and continuous improvement, including building offline/online evaluation harnesses, creating prompt libraries with versioning, and reducing hallucinations through verification and tool use. You will implement safety measures, conduct jailbreak/prompt-injection tests, policy checks, and PII handling, and collaborate with engineers to integrate prompts into production features. The position requires demonstrated prompt design experience, experience with eval datasets and automated scoring, familiarity with retrieval-augmented generation and tool calls, and strong scripting skills in Python/TypeScript. Knowledge of LangChain, vector stores, rerankers, safety tooling, red-teaming, and experimentation platforms is a plus.
Required Skills
Design, Content & Media
Visual Design
Engineering, Construction & Trades
Geotechnical EngineeringStructural Analysis
Soft Skills & Professional Competencies
CollaborationData Analysis
Finance, Legal & Governance
Valuation
Information Technology
PythonTypeScriptLangChainA/B TestingRAGSoftware Engineering
Business, Sales & Management
SAFe
Education & Training
Assessment Design
Science & Research
Data Analysis for Research
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-HavesExperience with LangChain/LLM orchestration, vector stores, and rerankers.Knowledge of safety tooling and red-teaming techniques.Experiment platforms (feature flags, A/B tests), analytics.
Description
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.
✨ Premium Match Details
Deep-dive CV analysis, customized Cover Letters, and Interview prep!
📊 Match Analysis
Insights against your active CV
📊
Personalized Match Analysis
Upload your CV to see exact matching percentages, detailed skills mapping, and gap analysis for this role.
🎯 Overalli74%
⚡ Skillsi85%
View Breakdown
Ontology Match: 85.0
Matched:✓ Requirements Matching✓ Ontology Skills Mapping
📜 Eligibilityi49%
View Breakdown
Local: 19600%
🏗️ Career Fiti91%
View Breakdown
Seniority: 91.0
📋 Requirementsi67%
View Breakdown
Domain: 67.0
🔥 Motivationi78%
View Breakdown
Title Fit: 78.00