A new approach to optimization in kinematic synthesis of mechanisms is presented which is based on simulated annealing, a probabilistic combinatorial optimization technique. The advantage of this technique is that it converges to the global optimum asymptotically. Simulated annealing has been successfully applied to solve several combinatorial optimization problems in the fields of computer-aided design of VLSI chips, image processing and graph theory. However, it has not been used as an optimization tool in the field of mechanical design. We solve three problems in kinematic synthesis using simulated annealing and the results show that the method is fast and obtains solutions at least as good as and in some cases better than those obtained by conventional optimization techniques.