AI Engineering Intern

Role overview A three-month internship embedded with the team building LLM-backed product features for client work. The role is hands-on: you will prototype retrieval pipelines, agentic workflows, and prompt iterations, then help wire them into real surfaces with appropriate guardrails.

Responsibilities - Develop and iterate on prompts, retrieval pipelines, and tool-calling agents powered by large language models. - Author evaluation scripts to measure whether a change actually improves quality or reliability. - Connect model output to live product surfaces, including reasonable safety guardrails around behavior and cost. - Experiment with emerging models and frameworks, then summarize what is genuinely worth adopting.

Requirements - Working proficiency in Python or TypeScript and comfort calling external APIs. - Prior experience building something concrete with an LLM API, whether a chatbot, a RAG demo, an agent, or a similar project. - Availability for the full three months, with a few hours of overlap with the team each day. - Willingness to question and evaluate model output critically rather than accepting the first response.

Nice to have - Exposure to embeddings, vector stores, or RAG architectures. - Familiarity with the Vercel AI SDK, LangChain, or similar frameworks. - Basic backend fundamentals such as API design and data modeling.