AI Engineer Intern

Role Overview

PipesHub is the open-source Context Layer for Enterprise AI. As an AI Engineer Intern, you will ship code into a public repo that other engineers read, fork, and file issues against, working on production AI systems at enterprise scale.

Responsibilities

• Improving retrieval quality through chunking, embedding choices, hybrid search, and reranking.
• Building and improving LangGraph workflows including tool calling and multi-step planning.
• Document understanding: converting various file formats into clean citable blocks.
• Building evaluation sets and tracing to measure model performance.
• Ensuring grounding by mapping claims back to real document blocks.
• Extending MCP servers and Python, TypeScript, and Go SDKs.

Requirements

• Strong Python programming skills with real-world debugging experience.
• Proven experience building with LLMs (API integrations, RAG pipelines, or agents).
• Working understanding of embeddings, vector search, and prompting.
• Familiarity with LangChain, LangGraph, or LlamaIndex.
• Proficiency with Git and ability to navigate unfamiliar codebases.

Nice to Have

• A public GitHub profile or deployed demo.
• Open-source contributions.
• Experience with FastAPI, Docker, Qdrant, Pinecone, Weaviate, or Neo4j.
• Exposure to knowledge graphs or information retrieval.
• Experience with eval tools like LangSmith, Ragas, or Phoenix.

Skills

• Python
• LangChain
• FastAPI
• Vector Search
• RAG