How machine learning libraries are created?

I would like to know how machine learning libraries (or in general libraries at large scale) are created. I mean Python doesn’t have inbuilt array system but c has. So how they are supported for Python and how do they start the thing and develop it as we know today as a final product (like NumPy) ?

P.S.- Let me know if this is not the right community for asking general computing questions because there is significant overlap among CS stack exchange forums and if it’s not right place then recommend the appropriate stack exchange platform for asking general computing questions.

Also, I couldn’t find relevant tags so had to tag it with machine learning.