Indeed MLE 电面

电面就是个系统设计, 根据whiteboard记录整理：

* How would you diagnose a spam classifier with high offline accuracy but poor production performance?
* If recall is low, how would you perform EDA and analyze false negatives?
* What features would you use to train a new spam/job-quality classifier?
* How does widespread LLM-generated content change your approach?
* How would you defend an LLM-based classifi

您好！
本帖隐藏的内容需要积分高于 188 才可浏览
您当前积分为 0。
使用VIP即刻解锁阅读权限或查看其他获取积分的方式

游客，您好！
本帖隐藏的内容需要积分高于 188 才可浏览
您当前积分为 0。
VIP即刻解锁阅读权限 或 查看其他获取积分的方式
Unlock interview details and practice with AI
Curated Interview Questions from Top Companies

determine whether the new model is statistically better?
* What does a p-value mean?
* How would you monitor the model after full deployment?
* How would you quantify data drift and concept drift?