AI Engineer Intern, LLM & AI Agents

AI Engineer Intern, LLM \& AI Agents **Location:** Remote within the United States, with optional collaboration in the San Francisco Bay Area **Type:** Paid, part-time internship **Schedule:** 15 to 20 hours per week **Duration:** 12 weeks, with the possibility of extension About Moonveil AI Moonveil AI helps companies launch production-ready AI agents in 4-8 weeks. We take one high-value business workflow and turn it into a reliable AI system that teams can use, launch, and own. Our work includes AI agents, retrieval systems, evaluations, tool integrations, human review workflows, and production deployment. We work with teams in finance, healthcare, and business operations, where accuracy, security, and reliability matter. About the Role We are looking for an AI Engineer Intern who wants to build real AI systems, not just experiment with prompts or complete tutorial projects. You will work directly with Moonveil’s founder and engineering team to prototype, build, test, and improve AI agents for real business workflows. Depending on your experience, you may contribute to internal tools, client projects, evaluation systems, or open technical resources. This is a hands-on engineering role. You will write code, test ideas, investigate failures, and help move working prototypes toward production. What You Will Do * Build and test AI agents using modern LLM APIs * Develop RAG and knowledge retrieval workflows * Connect agents to APIs, databases, and business tools * Create evaluations for accuracy, reliability, and tool use * Investigate failure cases and improve agent behavior * Implement logging, human review, and approval workflows * Contribute to Python or TypeScript applications * Document experiments, technical decisions, and results * Participate in code reviews and engineering discussions * Ship small but meaningful features that real users can test What We Are Looking For * Currently pursuing or recently completed a technical degree, bootcamp, or equivalent self-directed training * Experience building at least one working software or AI project * Comfortable writing code in Python or TypeScript * Familiarity with APIs, Git, debugging, and basic software engineering practices * Curiosity about LLMs, AI agents, RAG, evaluations, and production AI * Ability to work independently, communicate clearly, and ask good questions * Willingness to test your own work and learn from failures We care more about what you have built than where you studied. You do not need previous professional AI experience, and you do not need to meet every qualification before applying. Nice to Have * Experience with OpenAI, Anthropic, or other LLM APIs * Experience with agent frameworks, vector databases, or retrieval systems * Familiarity with Docker, cloud deployment, or backend development * Experience building evaluation datasets or automated tests * Contributions to open-source projects * A personal project involving AI agents or LLM applications What You Will Get * Direct experience building production-oriented AI systems * Regular technical feedback and mentorship * Exposure to real customer workflows and engineering decisions * Experience evaluating and improving AI reliability * Opportunities to own and ship meaningful work * Potential consideration for future contract or full-time opportunities How to Apply Please include: * Your LinkedIn profile * Your GitHub, portfolio, or project links * One project you are proud of * A short explanation of what you built and what you learned * A formal cover letter is not required. Show us what you have built and how you think.