Internship - Architectures

Fixed-term contract (typically 3 months) · 80–100% · Zürich · Students (Bachelor, Master or PhD level)

«Making sense of data is the winning competence in all industries.»

We build D ONE with the belief that every company will be a data company. Since our beginnings, we help our clients to make sense of their data and generate value.

In this internship you will work independently on a topic in the area of retrieval-augmented generation (RAG) system design. You will study the current state of the art, build and refine working software, measure what you build, and share your findings with our consultants and clients.

Your tasks will include:

• Reviewing the state of the art in retrieval-augmented generation and selecting approaches worth building on.
• Designing and implementing RAG components in clean, modular, well-tested Python.
• Running the same solution across local and cloud environments and reasoning about the trade-offs.
• Systematically benchmarking configurations and interpreting the results.
• Documenting your work and presenting it to a technical and a non-technical audience.

What you bring:

• Current enrollment in a Bachelor's, Master's or PhD programme in Computer Science, Data Science, Computational Linguistics, Engineering, Mathematics or a comparable field.
• Interest in at least one industry domain and curiosity about how data creates value in it.
• Down-to-earth and pragmatic results-oriented attitude.
• Experience in working with large data sets and databases.
• Knowledge in relevant technologies and programming languages (e.g. Python, SQL, Git, Spark, cloud platforms).
• Excellent communication skills in English; German is a strong plus.

Preferred qualifications:

• Working understanding of large language models, embeddings and vector search, and of how retrieval and generation interact.
• Hands-on experience with orchestration libraries such as LangChain, LlamaIndex or Haystack, and with vector stores such as pgvector, Qdrant, Weaviate, Chroma or FAISS.
• Familiarity with document ingestion, chunking and indexing strategies, and with hybrid retrieval (lexical and dense) and re-ranking.
• Software engineering discipline: modular package design, configuration management (e.g. Hydra, Pydantic settings), dependency management, unit testing and CI.
• Ability to run models both locally (e.g. Ollama, vLLM, llama.cpp) and via hosted APIs, and to containerise workloads with Docker.
• Exposure to at least one cloud platform (Azure, AWS or GCP) and its managed AI and vector services.