Prompt Engineer

IC Markets Global is one of the most renowned Forex CFD provider, offering trading solutions for active day traders and scalpers as well as traders that are new to the forex market. IC Markets Global offers its clients cutting edge trading platforms, low latency connectivity and superior liquidity.

IC Markets Global is revolutionizing online forex trading. Traders are now able to gain access to pricing previously only available to investment banks and high net worth individuals.

Our management team have significant experience in the Forex, CFD and Equity markets in Asia, Europe and North America. It is this experience that has enabled us to select the best possible technology solutions and hand pick some of the best pricing providers available in the market.

About the Role

We are looking for a talented and detail oriented Prompt Engineer to join our growing AI team. In this role, you will be responsible for crafting, evaluating, and optimizing prompts that drive the behavior 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.

Key Responsibilities

• Design, test, and systematically optimize prompts for LLM-powered applications and AI agent pipelines.


• Create and continuously refine system prompts, guardrails, evaluation prompts, and multi-agent interaction frameworks.


• Collaborate closely with AI backend engineers to seamlessly integrate prompts into production APIs and agent workflows.


• Develop comprehensive prompt evaluation datasets, scoring methodologies, and automated testing pipelines to ensure consistent quality.


• Experiment with Retrieval-Augmented Generation (RAG) pipelines, memory systems, tool-calling mechanisms, and agent orchestration strategies.


• Analyze agent failures and iterate on prompt designs using structured evaluation frameworks and real-world production feedback.


• Partner with product and business stakeholders to translate functional requirements into precise, well-defined AI behaviors.


• Document prompting strategies, established best practices, and maintain a library of reusable prompt templates for organizational use.


• Skills & Memory

Required Qualifications

• 2+ years of hands on experience working with Large Language Models (LLMs) and Generative AI in production environments.


• Strong command of prompt engineering techniques, including reasoning, information extraction, summarization, and agentic workflow design.


• Proven experience with synthetic dataset generation and AI evaluation methodologies.


• Familiarity with Model Context Protocols (MCP), AI gateways, and model routing strategies.


• Solid understanding of AI safety principles, prompt injection risks, and secure agent design practices.


• Experience working with AI frameworks such as LangChain, LangGraph, LlamaIndex, or equivalent.


• Demonstrated experience in building and evaluating AI agents utilizing tool-calling, RAG architectures, and memory systems.


• Strong understanding of hallucination mitigation strategies and their practical application in production system


• Experience with structured output generation and JSON schema design for LLM responses.


• Proven ability to design and implement evaluation pipelines assessing LLM quality, accuracy, latency, and safety.


• Comfortable working with Python and LangChain, with a strong ability to collaborate effectively with AI engineers.


• Hands-on experience with AI monitoring and evaluation tools such as LangSmith, DeepEval, Ragas, or similar platforms.


• Clear understanding of the distinctions between local and cloud-based LLM inferencing, and the implications of each in production contexts.