I'll never understand why Science/Nature carry any currency in CS and Math. TBH I consider them negative signals in these fields, and I encourage others to do the same when hiring -- the same way that a prestigious newspaper or magazine would treat someone with a bunch of (non-news) Buzzfeed bylines.
There are some exceptions. E.g., a Science/Nature paper summarizing several years worth of papers published in "real" venues. Truly novel work that's reported on for the first time in Nature/Science is almost universally garbage. At least in CS/Math.
In my experience, at least in pure math, publishing in Nature/Science doesn’t carry any weight. The most prestigious journals for a given subfield usually specialize in that subfield (with a name like Journal of Geometric Topology), with a few exceptions like Annals and JAMS. Even those are still focused heavily on pure math; I can’t think of any which are cross-disciplinary outside of math.
There are some exceptions. E.g., a Science/Nature paper summarizing several years worth of papers published in "real" venues. Truly novel work that's reported on for the first time in Nature/Science is almost universally garbage. At least in CS/Math.