Prompt Engineer

About the Role

We are hiring a Prompt Engineer to join our AI team and specialize in the art and science of working with large language models. You will design, test, and continuously optimize the prompts and AI workflows that power our client applications — from intelligent chatbots and document extractors to AI agent pipelines and automated content systems. This is a critical, high-leverage role at the intersection of language, logic, and AI product engineering.

Tech Stack

Requirements

• Strong analytical thinking and excellent written English — precision in language is critical for this role.
• Hands-on experience designing prompts for GPT-4, Claude, or other production LLMs.
• Understanding of LLM fundamentals: temperature, top_p, context windows, and model behaviour.
• Experience with prompt chaining, few-shot learning, chain-of-thought prompting, and retrieval-augmented generation.
• Ability to systematically test, evaluate, and improve prompt performance using benchmarking techniques.
• Comfortable writing Python scripts to automate prompt testing and integrate with APIs.
• Familiarity with AI agent architectures and multi-step task decomposition.

Responsibilities

• Design, document, and maintain prompt libraries for a variety of client use cases (chatbots, extraction, summarization, classification).
• Build and run prompt evaluation pipelines to benchmark accuracy, consistency, and hallucination rates.
• Collaborate with AI engineers to integrate optimized prompts into LangChain and LlamaIndex pipelines.
• Research and implement the latest prompting techniques (ReAct, Tree of Thought, Chain of Thought) to improve output quality.
• Iterate on prompts based on user feedback, production logs, and model behaviour analysis.
• Create structured prompt templates for new client projects, reducing AI integration setup time.
• Document prompt versions, performance results, and learnings in a centralized knowledge base.