Skip to content
View plip1e's full-sized avatar
1 follower · 2 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report plip1e

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
plip1e/README.md

Hi there 👋

I'm Paul, an Ironhack-trained AI engineer based in Bavaria, Germany. I work mainly in Python, with a growing interest in JavaScript/TypeScript and the occasional detour into Rust.

  • 🔭 I'm currently building TubeScholar - a multi-agent RAG research assistant that turns YouTube into a queryable, source-aware knowledge base. Every answer ships with a transparent trust assessment: speaker credentials verified against Wikidata, channel reputation scoring, and per-claim confidence - because a summarizer that can't tell you whether to trust the source is just a confident parrot.
    • Stack: LangGraph · LangChain · LangSmith · Chroma · Pinecone · FastAPI · Docker · Chainlit · Gemini
  • 💼 Open to AI/ML engineering, backend, and full-stack roles - remote (based in Germany) or on-site in Munich. Graduating IronHack July 2026, available for full-time work immediately.
  • 💬 Ask me about RAG pipelines, agent orchestration with LangGraph, or why similarity search is not a verification tool
  • ⚡ Fun fact: Former bartender in the German Alps - I pivoted from mixing drinks to mixing embeddings, and I can still explain a RAG pipeline to anyone at 2am
  • 📫 How to reach me: LinkedIn · pau.dupreez04@gmail.com

Pinned Loading

  1. TubeScholar TubeScholar Public

    TubeScholar turns YouTube into a queryable, source-aware knowledge base. Multi-agent RAG with credential checking, channel reputation, and claim-confidence scoring.

    Python