3
$\begingroup$

I am not sure if this is a relevant post here but:

I made it to the final round for the Machine Learing Engineer position at Facebook. The final round interview is virtual (thanks to Corona) and will consist of:

2 - General Algorithmic Coding questions
1 - Machine Learning Design
1 - General Systems Design
1 - Career Background

Most of these I know what I need to do to prepare but the content given to me for the Machine Learning Design is scarce to say the least but typical example questions for these are:

Design a newsfeed ranking algorithm
Design local search ranking
Design if an old post would be good for "On this Day" memories feature

This is the key highlights of what is expected for the Machine Learning Design interview:

You should be able to describe the components of an end-to-end ML system, including but not
limited to; model development, evaluation, and deployment.

You should be able to use existing toolsets to model the problem and break down its
components.

Be ready to analyze your approach while understanding the tradeoffs between your design
decisions.

We expect you to have a good understanding of common ML tools/techniques, but we do not
expect you to know and memorize every ML algorithm out there.

Now, although I know Machine learning decently well (I would like to think so) and I do mainly do Machine/Deep learning at my curreny job. I have never designed a Machine learning system. Thus I am not sure how to prepare for this particular portion of the interview and I have not really found much material online in terms of designing machine learning system.

Any advice would be greatly appreciated. My interview is set in the beginning week of April.

$\endgroup$
1
3
$\begingroup$

To wrap up you can have the following to prepare for ML interviews:

And don't forget Data Science Stack Exchange. On this site, you can have a lot of interesting questions and answers. If you don't know the answer for your interview question, feel free to drop it here.

$\endgroup$
2
$\begingroup$

Besides the amazing book suggested by @Carlos Mougan, you might also have a look at this one: https://github.com/chiphuyen/machine-learning-systems-design/blob/master/build/build1/consolidated.pdf

$\endgroup$
1
  • $\begingroup$ @Wolfy do let us know if you come across some other good resources :) $\endgroup$ – user1825567 Mar 22 '20 at 10:28

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.