AI Prompt Engineer

About the Role:

We are looking for a talented and curious Prompt Engineer to join our AI team. In this role, you will sit at the intersection of language, logic, and large language models - designing, testing, and refining the prompts that power our AI-driven products. You will work closely with business stakeholders to deliver consistent, high-quality AI experiences to our users.

Role & responsibilities

• Design, iterate, and systematically evaluate prompts for LLMs such as Claude, GPT-4, and Gemini across a variety of product use cases.
• Build and maintain a prompt library with versioning, documentation, and performance benchmarks.
• Develop structured evaluation frameworks (evals) to measure output quality, accuracy, tone, and safety.
• Stay current with the rapidly evolving LLM landscape - new models, capabilities, context window sizes, and prompting techniques.
• Document best practices and mentor team members on effective prompting strategies

Preferred candidate profile

• 1+ year of experience working directly with LLMs in a professional setting.
• Deep familiarity with advanced prompting techniques: chain-of-thought, few-shot, zero-shot, ReAct, tree-of-thought, and structured output prompting.
• Strong analytical and experimental mindset - comfortable designing controlled prompt experiments and interpreting results.
• Excellent written communication skills with a sharp understanding of language, tone, and ambiguity.

Core Skills: Large Language Models | Chain-of-thought prompting | Prompt evaluation