Internship - Retrieval-Augmented Generation Architectures

About the role

D ONE helps companies make sense of their data and turn it into value. This internship is a fixed-term contract of typically 3 months at 80-100% in Zurich, open to students (Bachelor, Master or PhD) who will work independently on a topic in retrieval-augmented generation (RAG) system design. You will study the state of the art, build and refine working software, measure your results and share them with consultants and clients.

Key responsibilities

• Review the state of the art in RAG and select approaches worth building on.
• Design and implement RAG components in clean, modular, well-tested Python.
• Run the same solution locally and in the cloud, weighing the trade-offs.
• Benchmark configurations systematically and interpret the results.
• Document your work and present it to technical and non-technical audiences.

Required profile

• Current enrolment 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.
• Experience with large data sets and databases.
• Excellent English; German is a strong plus.

Required skills

• Knowledge of relevant technologies and programming languages (e.g. Python, SQL, Git, Spark, cloud platforms).
• Preferred: LLMs, embeddings, vector search, LangChain, LlamaIndex, Haystack, pgvector, Qdrant, Weaviate, Chroma, FAISS, Docker, Azure/AWS/GCP, MLflow, Weights & Biases.

What we offer

• A low-noise environment and an international team.
• Mentoring by senior consultants and access to the D ONE Academy.
• A clearly scoped topic you can shape, frequent offsite events and a realistic path to becoming a consultant.