[jrumbut]

That is very useful work to squeeze more performance out of existing software, I would say there is still a lot more to be gained from big wins in more efficiently distributing computing power like cloud computing and containerization (which are the kind of non-obvious ideas that require systems research to happen before implementation).

I'm not a systems researcher on the verge of becoming a millionaire so I don't know what those ideas are but anyone can see the untapped potential is enormous.