Remote AI Prompt Engineer (NLP & LLM)

We are seeking a Remote AI Prompt Engineer with strong NLP and LLM expertise to design, evaluate, and refine prompts that power production-grade AI applications. In this role, you will collaborate with product, engineering, and research teams to build high-quality LLM apps, RAG systems, and AI-driven product workflows. You will iterate on prompt strategies, measure model behavior, and translate business requirements into reliable, context-aware interactions. The position is fully remote and suited for candidates who thrive at the intersection of language, data, and user experience.

Day to day, you will craft and test prompt templates, build evaluation harnesses, analyze failure modes, and partner on retrieval pipelines that ground model outputs in accurate, domain-specific knowledge. You will help define quality standards, document best practices, and contribute to continuous improvement of AI product workflows. This is an opportunity to shape how users experience modern generative AI while working across a distributed, cross-functional team.

• Bachelor's degree in Computer Science, Linguistics, Data Science, or related field
• 2+ years of experience working with large language models and prompt design
• Strong understanding of NLP concepts, embeddings, and retrieval-augmented generation (RAG)
• Proficiency in Python and familiarity with LLM APIs and evaluation tooling
• Experience building or testing LLM applications and AI product workflows
• Excellent written communication and ability to iterate on ambiguous problems
• Remote-friendly with strong asynchronous collaboration skills