Prompt Engineering Intern

About the Role

Ready to shape how AI thinks and responds? As a Prompt Engineering Intern at Agentic Academy Labs, you'll dive deep into the art and science of crafting prompts that unlock the true potential of large language models. You'll work alongside our AI educators and engineers to build the next generation of agentic workflows, design evaluation harnesses, and create high-quality learning content that teaches thousands of students how to build with AI.

This isn't just about writing clever prompts; it's about building systems that reliably produce great outputs, designing tests to catch failure modes, and turning prompt techniques into teachable moments. If you're fascinated by how small changes in wording can lead to dramatically different results, this internship is your playground.

What You Will Do

• Design, iterate on, and refine prompts for a variety of LLM-powered agents and educational use cases
• Build and maintain evaluation harnesses to measure prompt performance, consistency, and output quality
• Collaborate with curriculum designers to translate prompt engineering concepts into student-friendly lessons and hands-on labs
• Develop agent workflows that chain together multiple prompts, tools, and reasoning steps
• Conduct prompt audits and failure analysis to identify edge cases and improve robustness
• Contribute to internal tooling that helps educators and developers test and deploy prompts at scale
• Document best practices, patterns, and anti-patterns in prompt design for reuse across the platform

Why Join Us

• Gain real-world experience working with cutting-edge LLMs and agentic frameworks in 2026's rapidly evolving AI landscape
• Build a portfolio of prompt systems, eval harnesses, and agent workflows that you can showcase to future employers
• Work directly with AI educators and engineers who are defining how the next generation learns to build with AI
• Flexible remote schedule designed for students, with async collaboration and supportive mentorship
• Opportunity to publish your work, speak at internal tech talks, and contribute to open-source AI education tools
• Stipend and academic credit support for qualifying students

Requirements

• Currently pursuing a degree in Computer Science, Artificial Intelligence, Data Science, or a related technical field
• Strong written communication skills and a knack for explaining complex ideas clearly
• Familiarity with at least one major LLM API (OpenAI, Anthropic, Google, etc.) and hands-on experience writing or testing prompts
• Basic understanding of how LLMs work, including concepts like temperature, token limits, and few-shot learning
• Comfortable working in a collaborative, remote environment with async communication tools

Preferred Qualifications

• Experience with Python or JavaScript and scripting for prompt iteration or evaluation
• Knowledge of prompt evaluation frameworks or experience building custom eval harnesses
• Familiarity with agent frameworks like LangChain, LlamaIndex, or custom agent loops
• Portfolio or project examples demonstrating prompt design, agent workflows, or content quality improvements
• Interest in AI education and translating technical concepts into learning experiences

What You'll Learn

• Advanced prompt design techniques for reasoning, creativity, and reliability
• How to build and run evaluation harnesses that catch hallucinations and edge cases
• Principles of agentic workflow design and orchestration
• How to balance prompt performance with cost, latency, and user experience
• Best practices for content quality assurance in AI-generated educational materials