Sonatus·Software Engineer·Onsite - System Design / Architecture
Apr 2026
System design round at Sonatus focused entirely on building a RAG pipeline for vehicle documentation. Pretty deep dive, covered everything from ingestion to evaluation metrics, and I left feeling like I'd either nailed it or completely talked myself in circles.
- Design a RAG system for vehicle documentation that ingests PDFs, HTML, and structured data, stores embeddings in a vector index, and powers an AI chatbot with grounded answers.
- How would you approach the retrieval strategy, and what are the tradeoffs between BM25, dense vector search, and a hybrid approach?
- How would you construct the prompt to ground the LLM's response in retrieved chunks and prevent hallucination?
- How would you evaluate the quality of the RAG system, specifically around faithfulness and groundedness?
- How do you handle freshness in the system when the underlying vehicle documentation is updated frequently?
“This was the whole interview, basically.” The rest of the author's notes on Software Engineer interview at Sonatus, Onsite - System Design / Architecture round, covers how they worked through the question, what the panel pushed back on, and what they would do differently.
View Post