EngineeringInternship-Summer

We are looking for a tech intern who wants to get their hands on a real infrastructure problem at the frontier of AI. This is not an internship where you sit on the sidelines; at Redpine, you will work directly with our engineering team to build the data layer that powers the next generation of AI models and agents. You will be embedded in the core product, owning a scoped problem from day one and shipping something that matters. If you are technically sharp, curious about how AI systems actually work under the hood, and ready to contribute from the start - this is your launchpad. Key responsibilities - Retrieval & Data Quality: Work on the pipelines that ingest, chunk, embed, and surface licensed data - improving precision, recall, and consistency across domains. - Evaluation & Testing: Write evals that measure dataset and retrieval quality in a structured, repeatable way. Help us know when things get better and when they don't. - Developer Tooling: Contribute to the internal and external-facing tools that make Redpine easier to build on - docs, SDKs, demo environments, or agentic workflow prototypes. - Ad-hoc Projects: Support the wider team with technical tasks that remove friction and move the platform forward - scope depends on where you fit and what we need most. Qualifications - Strong track record: Current student or recent graduate in computer science, engineering, or a related field, who has consistently performed at a high level in academics or extracurriculars. - Builder mindset: You have built things outside of coursework - side projects, open source, hackathons. You don't wait to be told what to do next. - Technical foundation: Comfortable in Python, Go, or Rust. You understand how LLMs and retrieval systems work, not just as a user. - Agile fast learner: You grasp new systems quickly, ask good questions, and thrive in a fast-paced, low-structure environment. - Experience is a plus: Familiarity with vector databases, embeddings, RAG pipelines, MCP, or