Prompt Engineering Intern

Roles And Responsibilities

• Design and iterate on prompts for LLM-based features (e.g., summarization, classification, extraction, data transformation, etc.).
• Conduct rapid experiments to evaluate and compare model outputs across - different prompt structures.
• Analyze prompt performance using accuracy, relevancy, and consistency benchmarks.
• Collaborate with product managers, engineers, and QA to integrate prompt workflows into production environments.
• Maintain and organize prompt libraries and performance benchmarks for reuse and refinement.
• Stay up to date with the latest advancements in prompting techniques, prompt tuning, and LLM capabilities.
• Contribute to prompt evaluation frameworks or internal tooling where needed.
  

Requirements

• Strong written communication skills and attention to detail.
• Demonstrated interest in AI, natural language processing, or large language models (via coursework, side projects, or prior experience).
• Comfortable with basic programming in Python or JavaScript to run tests or evaluate outputs.
• Ability to think critically, analyze outputs, and refine instructions based on results.
• Comfortable reading and understanding product requirements or user problems, and translating them into prompt logic.
  

Good to Have

• Familiarity with tools like OpenAI GPT, Claude, Gemini, LangChain, or LlamaIndex.
• Experience working with REST APIs or building simple scripts to automate tasks.
• Background in linguistics, cognitive science, computer science, or related fields.
• Experience working with vector search, embeddings, or retrieval-augmented generation (RAG).