Learning From Data (https://amlbook.com) is a great introduction to ML from a more theoretical perspective. The language is easy to understand but the concepts that it deals with are very theoretical, a combination that is hard to find elsewhere.

For example nearly everyone understands how to apply multivariable logistic regression, in say Numpy, however a good grasp of underlying concepts such as confidence bounds for overfitting and and being able to use formal proofs to explain concepts such as VC Generalisation will both help you stand out and provide a good foundation that makes further learning much easier.