It was all good, the interviewer was very nice. Technical questions were a bit challenging but overall it was good. The hiring manager was looking for some hands on experience
Average interview
Application
I applied online. The process took 4 weeks. I interviewed at Google in Dec 2016
Interview
Submit resume online, answer a questionnaire with about 20 questions. Then a HR arranged a phone interview and attached a review guide. I followed the guide for reviewing. But during the interview, most of questions are from my keys words in my resume. So understand and prepare explaining everything in your resume.
Interview questions [1]
Question 1
1. Why use feature selection? If two predictors are highly correlated, what is the effect on the coefficients in the logistic regression? What are the confidence intervals of the coefficients?
2. K- mean and Gaussian mixture model: what is the difference between K-mean and EM?
3.How to decided k?
4.When using Gaussian mixture model, how do you know it is applicable? (Normal distribution)
4.If the labels are known in the clustering project, how to evaluate the performance of the model? In my project, I use adjusted rank index? But I forgot how it is defined.
Back to back interview.
[1]. Mainly ask ML concepts, e.g., how to develop a classifer for youtube video; they will also ask some statistical concepts
[2] Coding for both python and sql
Applied at PhD level so I had two back to back technical interviews. One all stats concepts and the other talking over a hypothetical experiment design and walking through my thought process.
