Designing and implementing new and general algorithms for the noisy intermediate scale quantum (NISQ) computers that will soon be available is not easy. In previous work we have suggested, and developed, the idea of using machine learning techniques to train a small quantum system such that the desired process is "learned," thus obviating the algorithm design difficulty. Here, we extend our results towards implementation on NISQ machines. We reverse engineer our learned two-qubit entanglement witness for implementation on Microsoft's Quantum Development Kit and IBM's Quantum Experience; and, using the machine learning technique called "bootstrapping", we infer the pattern for mesoscopic N from simulation results for three-, four-, five-, six-, and seven-qubit systems. The learned witness is robust to noise and decoherence. Our results suggest a fruitful pathway for general quantum computer algorithm design and computation.