This all comes down to meaning. As you've obviously understood, the structure of the sentence allows for two possible parsings, giving rise to two different meanings, which I could represent like this:
a) The customer is waiting for the clerks behind the fruit display.
b) The customer is waiting for the clerks behind the fruit display.
Is there anything in either syntactic structure itself, absent context, that contributes to one possible interpretation over another? I think another way of framing this is to ask whether there is any psycholinguistic bias in the mind towards one parsing over the other? Do we have some kind of tendency to favour simpler structures over more complex ones, for example? Or do we tend to interpret more readily those structures to which we've had greater exposure over the course of our lives?
My feeling is that there isn't any such bias, and that the initial interpretation comes from the mental picture that occurs immediately to the mind at the moment of hearing. This mental picture likely comes from our experience of and expectations about the world and how we resultingly make sense of its parts. In this case, I think the interpretation that it's the customer who is behind the desk is the more likely for the majority of people.
It's a very interesting question. I'd be very curious to know what proportion of native speakers would like me initially interpret sentence a. Perhaps we could do a little poll?