In this work, we study the problem of relay beamforming for an underlay cognitive radio relay network using amplify-and-forward (AF) relaying technique. We consider a cognitive radio network consisting of single primary and multiple secondary transmitters/receivers. In addition, there are several relay nodes that help both primary and secondary networks. We propose a new beamforming method for relays' transmission, in which the beamforming weights at the relays are the solution of an optimization problem. The objective of the optimization problem is maximizing the worst case signal to interference plus noise ratio (SINR) at the secondary receivers (SU-RX) and the constraints are the interference power on the primary receiver (PU-RX) and the total transmitted power of the relay nodes. We show that the beamforming problem can be reformulated as a second order cone programming (SOCP) problem and solved by the bisection search method. Our simulation results show the performance improvement as a function of the size and the power of the relay network.