Role: Prompt Engineer
Experience: 5+ Years
Dubai Based Role
About the Role
We are looking for a Prompt Engineer to join our AI team and build reliable, production-grade experiences powered by Large Language Models (LLMs).
You will design and optimize prompts, build and evaluate AI agents, improve RAG and tool-calling workflows, and develop evaluation frameworks that ensure AI systems are accurate, safe, consistent, and production-ready.
This is a hands-on engineering role for someone who understands both prompt engineering and the underlying GenAI/LLM application stack.
What You'll Do
- Design, test, and optimize prompts for LLM applications and AI agents.
- Build system prompts, guardrails, evaluation prompts, and reusable prompt templates.
- Develop and evaluate AI agents using RAG, tool calling, memory, and multi-agent workflows.
- Create synthetic datasets and evaluation benchmarks for LLM applications.
- Build automated evaluation pipelines to measure accuracy, quality, latency, reliability, and safety.
- Analyze LLM and agent failures and continuously improve system behavior.
- Work with AI engineers to integrate prompts and agent workflows into production APIs.
- Translate product and business requirements into precise AI behaviors.
- Implement techniques for hallucination reduction, prompt-injection protection, and secure agent design.
- Work with structured outputs, function calling, and JSON Schema.
- Experiment with MCP, AI gateways, model routing, and different LLM inference approaches.
- Document prompt strategies, evaluation methodologies, and AI engineering best practices.
What We're Looking For
- 5+ years of hands-on experience with LLMs and Generative AI in production.
- Strong expertise in Prompt Engineering across reasoning, extraction, summarization, classification, and agentic workflows.
- Strong experience building AI agents with RAG, tool calling, and memory.
- Hands-on experience with LangChain, LangGraph, LlamaIndex, or equivalent frameworks.
- Experience with synthetic data generation and LLM evaluation.
- Strong understanding of hallucination mitigation, AI safety, guardrails, and prompt injection risks.
- Experience with structured outputs and JSON Schema.
- Strong Python programming skills and ability to work with AI/ML APIs.
- Experience with evaluation and observability platforms such as LangSmith, DeepEval, Ragas, or similar.
- Understanding of MCP, AI gateways, and model routing.
- Understanding of cloud vs. local LLM inference, including latency, scalability, security, and cost considerations.
- Strong communication and collaboration skills with product and engineering teams.
Nice to Have
- Experience with OpenAI, Anthropic, Gemini, Llama, Mistral, or similar models.
- Experience with vector databases and embedding models.
- Experience building production-grade GenAI APIs.
- Experience with multi-agent architectures and agent orchestration.
- Experience in financial services, trading, Forex, or other regulated environments.