Prompt Engineer

Hire Rightt - Executive Search & HR Advisory; Dubai; On-site; AED 300,000 - 480,000; Full time

Benefits offered by this job

LangSmith

DeepEval

Job summary

Hire Rightt - Executive Search & HR Advisory in Dubai seeks a specialist to craft, evaluate, and optimize prompts driving LLM-powered applications and intelligent agents in production. You will bridge business requirements and AI outcomes, ensuring systems perform accurately, safely, and reliably.

You will design prompt architectures, implement evaluation pipelines, and collaborate with AI/ML teams to deliver structured outputs and robust monitoring using tools like LangSmith and RAG memory.

Qualifications

• 3+ years hands-on experience with LLMs and Generative AI in production.
• Prompt engineering including reasoning, information extraction and summarisation, and agentic workflow design.
• Familiarity with Model Context Protocol (MCP), AI gateways, and model routing strategies.
• Strong understanding of AI safety, prompt injection risks, and secure agent design.
• Experience with AI frameworks such as LangChain, LangGraph, LlamaIndex or equivalent.
• Hands-on experience building and evaluating AI agents using tool calling, RAG architectures and memory systems.
• Understanding hallucination mitigation in production systems.
• Experience with structured output generation and JSON Schema for LLM responses.
• Design and implementation of LLM evaluation pipelines measuring quality, latency, and safety.
• Strong Python skills and collaboration with AI/ML engineering teams.
• Hands-on experience with AI monitoring tools such as LangSmith, DeepEval, Ragas.

Skills

LLMs & Generative AI

Prompt engineering

Information extraction

Summarisation

Agentic workflow design

AI safety

LLM evaluation pipelines

Python

AI monitoring

Tools

LangChain

LangGraph

LlamaIndex

LangSmith

DeepEval

Ragas

Job description

In this role, you will be responsible for crafting, evaluating, and optimizing prompts that drive the behaviour of LLM-powered applications and intelligent agent systems. You will play a pivotal role in bridging the gap between business requirements and AI-driven outcomes, ensuring that our systems perform accurately, safely, and reliably in production.

Requirements

• 3+ years of hands-on experience working with Large Language Models (LLMs) and Generative AI in production environments.
• Strong expertise in prompt engineering, including reasoning, information extraction, summarisation, and agentic workflow design.
• Familiarity with Model Context Protocol (MCP), AI gateways, and model routing strategies.
• Strong understanding of AI safety, prompt injection risks, and secure agent design.
• Experience with AI frameworks such as LangChain, LangGraph, LlamaIndex, or equivalent.
• Hands-on experience building and evaluating AI agents using tool calling, RAG architectures, and memory systems.
• Strong understanding of hallucination mitigation and its practical application in production systems.
• Experience with structured output generation and JSON Schema for LLM responses.
• Proven ability to design and implement LLM evaluation pipelines measuring quality, accuracy, latency, and safety.
• Strong Python skills, with the ability to collaborate effectively with AI/ML engineering teams.
• Hands-on experience with AI monitoring and evaluation tools such as LangSmith, DeepEval, Ragas, or similar platforms.
• Understanding of local vs. cloud-based LLM inference and the implications of each in production environments.