Tangerine AI Engineer Interview Questions
The questions to prepare for a Tangerine AI Engineer interview. Questions from real interview reports rank first. Updated daily.
Design a low-latency, cost-aware serving platform for multiple fine-tuned LLMs under variable traffic.
Design an LLM serving system that balances latency, cost, scalability, and safety for production traffic.
Explain how to manage memory, summarization, retrieval, and safety in a long-running LLM agent when context exceeds the model window.
Explain how to evaluate a generative model using offline and online methods, with attention to hallucination, product metrics, and experiment design.
Tests ability to build efficient retrieval-augmented generation pipelines.
Detect transaction indices whose values exceed a rolling sample-standard-deviation threshold using an O(n) sliding window.
Assesses scalable embedding storage and vector retrieval design.
Tests understanding of quantitative evaluation for production-grade LLMs.
Sign up to see every question
Create a free account to unlock this list and practice real interview questions.