In this paper, a global optimization technique is applied to solve the otimal transmitter placement problem for indoor wireless systems. An efficient pattern search algorithm - DIRECT (DIviding RECTangles) of Jones, Perttunen, and Stuckman (1993) - has been connected to a parallel 3D radio propagation ray tracing modeler running on a 200-node Beowulf cluster of Linux workstations. Surrogate functions for a parallel WCDMA (wideband code division multiple access) simulator were used to estimate the system performance for the global optimization algorithm. Power coverage and BER (bit error rate) are considered as two different criteria for optimizing locations of a specified number of transmitters across the feasible region of the design space. This paper briefly describes the underlying radio propagation and WCDMA simulations and focuses on the design issues of the optimization loop.