Internship - Retrieval-Augmented Generation Architectures (Zurich, Switzerland)
Core
Design and implement Retrieval-Augmented Generation (RAG) system components, benchmark configurations, and document findings for clients.
Role type
Intern, RAG Architect
Builds
RAG system components and prototypes
Domain
Data Science / AI / Large Language Models
Deliverable
production ML models
Required skills
Python, SQL, Git, Spark, cloud platforms, large datasets, databases
Preferred skills
LLMs, embeddings, vector search, LangChain, LlamaIndex, Haystack, pgvector, Qdrant, Weaviate, Chroma, FAISS, document ingestion, chunking, indexing, hybrid retrieval, re-ranking, modular package design, Hydra, Pydantic, unit testing, CI, Ollama, vLLM, llama.cpp, Docker, Azure, AWS, GCP, MLflow, Weights & Biases, parameter sweeps, experiment tracking, latency optimization, token economics, caching
