Description
About the role
Arcline builds AI-powered data tools that help K-12 school districts turn fragmented student data into clear, actionable decisions. We work with superintendents and district leaders across Alabama, California, Kentucky, Texas, Wisconsin, and more — replacing months of manual reporting with instant, AI-driven answers.
We're a small, AI-native team that ships fast and builds with real users. Our interns ship real features to real classrooms.
You'll work on the core intelligence layer that powers Arcline's natural language query engine — the system that lets educators ask questions in plain English and get accurate, cited answers from their district's data.
Day to day
Build and improve RAG pipelines and agent workflows using LangChain, LlamaIndex, and vector databases (pgvector, Pinecone)
Preprocess and normalize messy education data from multiple district sources for use in ML pipelines
Evaluate retrieval quality, answer accuracy, and prompt performance across real district datasets
Build evaluation harnesses and benchmarks to systematically measure and improve model output
Work with the founding engineering team to ship improvements directly to production
Requirements
Currently pursuing a B.S./B.A. or M.S. in Computer Science, Machine Learning, Data Science, or a related field
Familiarity with ML concepts — you've taken coursework or done projects involving embeddings, retrieval, or model evaluation
Proficiency in Python
Able to commit to a 10-week internship fr
Employer contacts (email/phone/telegram) are hidden from the public preview —
send your CV, and we will connect you directly.